Sunday, October 12, 2025

Western capercaillie: "Nobel Peace Prize 1947 Award ceremony speech Presentation Speech by Gunnar Jahn*, Chairman of the Nobel Committee The Nobel Committee of the Norwegian Parliament has awarded this year’s Peace Prize to the Quakers, represented by their two great relief organizations ..." * * * World University and School Manifesto - Thanks to Anthropic AI & Haiku-ish . . . 'Reminder EE: @WorldUnivAndSch is FREE, MIT & Wiki' * * searched on - 'history of manifestos in the 1960s in America' AND searched on 'Yoga and dissent 1960s America' But I also find Yoga meditation unifying too regarding an inner releasing actions and explorations and consciousness * * * I continue to get these AI and Robotics + researchers' academic papers in my email box, compiled by UC Berkeley Prof Anca Dragan (originally from Germany) ... and which related papers will be helpful in developing MIT OCW-centric wiki World University and School's Robotics and Artificial Intelligence and Machine Learning and Large Language Models in all 200 countries and in all 7159 known living languages ... and in a #RealisticVirtualEarth #ForRobotics and #ForEverything ... * * * To William Hague, the new Chancellor of Oxford University ~ #OxfordWUaScollaborations ?

 

This is the most inspiring Quaker writing I know of - 


Nobel Peace Prize 1947 

Award ceremony speech

 

Presentation Speech by Gunnar Jahn*, Chairman of the Nobel Committee 


The Nobel Committee of the Norwegian Parliament has awarded this year’s Peace Prize to the Quakers, represented by their two great relief organizations, the Friends Service Council in London and the American Friends Service Committee in Philadelphia.

https://www.nobelprize.org/prizes/peace/1947/ceremony-speech/


. . . 

"This is the message of good deeds, the message that men can find each other in spite of war, in spite of differences in race. Is it not here that we have the hope of laying foundations for peace among nations, of building it up in man himself so that the settling of disputes by force becomes impossible? All of us know that we have not yet traveled far along this road. And yet – when we witness today the great willingness to help those who have suffered, a generosity unknown before the war and often greatest among those who have least, can we not hope that there is something in the heart of man on which we can build, that we can one day reach our goal if only it be possible to make contact with people in all lands?"




* 

searched today on ...

"greatest Quaker writings Nobel peace prize address for 1947 by Gunnar Jahn +"





 

We utterly deny all outward wars and strife and
fighting with outward weapons for any end or under any pretense whatever;
this is our testimony to the whole world

George Fox and others, to Charles II
of England, 1660/61 (1)���






Found too - 


Some of the greatest Quaker writings include the journals of George Fox and John Woolman, as well as Thomas Kelly's A Testament of Devotion. Other significant works are the writings of Rufus Jones, the historical studies by William C. Braithwaite, and books that explore specific Quaker themes like peace or simplicity, such as Quaker.org's list of recommended readings. 
Classic foundational texts
  • The Journal of George Fox: The spiritual autobiography of one of the founders of Quakerism, detailing his experiences and the early days of the movement.
  • The Journal of John Woolman: Considered a masterpiece of spiritual autobiography, this journal is known for its deep introspection and powerful witness against slavery and war. 
Devotional and theological works
  • A Testament of Devotion by Thomas Kelly: A widely read book that explores the inner life and the experience of God's presence, often cited as a key text in Quaker spirituality.
  • The Inner Life by Rufus M. Jones: A work by a prolific and influential Quaker thinker, exploring the nature of spiritual experience and the "inner light".



* * 

Nobel Prize 
Friends Meeting of Cambridge, MA - https://fmcquaker.org/ - Sunday 9/28/25

TwitterX - 
Greetings. This is the most inspiring #QuakerWriting I know of: #NobelPeacePrize1947: Award ceremony speech by #GunnarJahn
https://www.nobelprize.org/prizes/peace/1947/ceremony-speech/
What are inspiring #QuakerWritings for you/thee? Glad to have attended #SilentQuakerMeetingOnline this morn https://fmcquaker.org/calendar/~

https://x.com/scottmacleod/status/1972338999709893057

https://x.com/Q_YogaMacFlower/status/1972338487174234419

https://x.com/sgkmacleod/status/1972338858919612740


*

Greetings. This is the most inspiring Quaker writing that I know of: The Nobel peace prize address 1947 by Gunnar Jahn

Nobel Peace Prize 1947: Award ceremony speech
 
Presentation Speech by Gunnar Jahn*, Chairman of the Nobel Committee
https://www.nobelprize.org/prizes/peace/1947/ceremony-speech/

What are inspiring Quaker writings for you / thee?


Scott ~Friendly-inspired: sgkmacleod@worlduniversityandschool.org

Scott GK MacLeod ~ https://x.com/Q_YogaMacFlower

https://fmcquaker.org/calendar/ 

* 




most inspiring Quaker writing that I know of: The Nobel peace prize address 1947 by Gunnar Jahn

https://www.nobelprize.org/prizes/peace/1947/ceremony-speech/





* * * 

World University and School Manifesto - Thanks to Anthropic AI & Haiku-ish 


'Reminder EE:
@WorldUnivAndSch is FREE,
MIT &
Wiki'

(#HaikuIsh & #MITOCWcentric)
New Manifesto - #WorldUniversityAndSchool: A Manifesto for #UniversalFreeEducation https://claude.ai/public/artifacts/7b17f5a8-9210-4433-9ef7-a9bbd05d0a88 : "The Vision: Education for All 7.9 Billion & coding for all 7,159 known living languages"

https://x.com/scottmacleod/status/1977199363345772970

https://x.com/WorldUnivAndSch/status/1977198659969466586

https://x.com/WUaSPress/status/1977199132487086105

https://x.com/HarbinBook/status/1977199270051955051

https://x.com/Q_YogaMacFlower/status/1977198855419838792

https://x.com/sgkmacleod/status/1977199011129180549

https://x.com/TheOpenBand/status/1977199542186676478



AND 


Great: "#WorldUniversityAndSchool: A Manifesto for #UniversalFreeEducation"
signed up w #AnthropicClaudeAI
with -
"#ScottGKMacLeod scottmacleod.com @ free #MITOCWcentric wiki @WorldUnivAndSch"
per #WUaSmanifesto -https://claude.ai/public/artifacts/7b17f5a8-9210-4433-9ef7-a9bbd05d0a88 -https://scott-macleod.blogspot.com/2025/12/fairweather-range-ak.html @npseaver~

https://x.com/WorldUnivAndSch/status/1977101162429268458

https://x.com/scottmacleod/status/1977102619308179690

https://x.com/Q_YogaMacFlower/status/1977103015560794219

https://x.com/TheOpenBand/status/1977102455533109751

https://x.com/HarbinBook/status/1977101905034985551

https://x.com/WUaSPress/status/1977101956436168884

https://x.com/sgkmacleod/status/1977102089177514305




* *


searched on - 

'history of manifestos in the 1960s in America'


and regarding - 

"World University and School: A Manifesto for Universal Free Education" (Sat 11 Oct 2025)
https://claude.ai/chat/c1cb5e72-d025-4fa1-818f-2eba10fa2f9e


(Manifesto definitions (from Apple dictionary on MacBook Air Laptop )

a public declaration of policy and aims 

A manifesto is a written declaration of the intentions, motives, or views of the issuer, be it an individual, group, political party, or government. A manifesto can accept a previously published opinion or public consensus, but many prominent manifestos—such as The Communist Manifesto and those of various artistic movements—reject accepted knowledge in favor of a new idea. Manifestos relating to religious belief are generally referred to as creeds or confessions of faith)



Manifestos in 1960s America were crucial documents of dissent that articulated the demands, ideologies, and visions of emerging social and political movements. Unlike the unified protest movements of earlier eras, the decade saw a proliferation of manifestos from diverse groups, each addressing specific grievances related to civil rights, feminism, student rights, and anti-war activism. [1, 2, 3, 4]

Civil rights and Black Power
Black Panther Party's Ten-Point Program (1966):
  • Context: Founded by Huey P. Newton and Bobby Seale in Oakland, California, the Black Panther Party was a revolutionary organization that sought to protect African American communities from police brutality. The Ten-Point Program articulated its demands for economic, social, and political justice.
  • Key Demands:
    • "What We Want": The list of demands included freedom, full employment, decent housing, and education that teaches "our true history".
    • "What We Believe": This section provided the philosophical justification for the demands, arguing for the right of Black people to self-determination and self-defense against a racist government.

  • Legacy: The Ten-Point Program became one of the most influential documents of the Black nationalist movement and inspired other groups, like the Brown Berets and the Young Lords. [5, 6, 7, 8]

"Letter from Birmingham Jail" (1963):
  • Context: While not a traditional manifesto, Martin Luther King Jr.'s open letter, written while he was incarcerated for protesting segregation, functions as a powerful declaration of civil rights principles.
  • Argument: King defends the strategy of nonviolent resistance, arguing that it is a moral and effective tool for social change. He famously declared that "injustice anywhere is a threat to justice everywhere".
  • Influence: This document rallied support for the civil rights movement and remains a foundational text on civil disobedience. [9, 10, 11, 12, 13]

The New Left and student movements
The Port Huron Statement (1962):
  • Context: This manifesto was adopted by the newly formed student activist group, Students for a Democratic Society (SDS), at a convention in Port Huron, Michigan. Written primarily by Tom Hayden, it captured the disillusionment of young people with the established political system.
  • Key Concepts:
    • Participatory Democracy: The document's central idea called for a more democratic society in which individuals have a greater say in the decisions affecting their lives.
    • Rejection of the Status Quo: It criticized racial bigotry, Cold War politics, and the apathy of the older generation.

  • Influence: The Port Huron Statement was a foundational text for the New Left and greatly influenced student activism and the anti-war movement. [14, 15, 16, 17, 18]

"You Don't Need a Weatherman to Know Which Way the Wind Blows" (1969):
  • Context: This position paper was the founding document of the radical Weatherman faction of SDS, which believed that nonviolent tactics were failing.
  • Ideology: It espoused a Marxist-Leninist view of the U.S. as an imperialist power and called for a violent, revolutionary movement to ally with anti-imperialist forces and black liberation movements.
  • Tactics: The manifesto advocated for creating a clandestine, revolutionary party and engaging in urban guerrilla warfare and bombings. [19, 20, 21, 22]

The feminist movement
"The Statement of Purpose" (1966):
  • Context: In 1966, the National Organization for Women (NOW) was founded by prominent feminists like Betty Friedan. The organization's statement outlined its reformist approach to achieving gender equality.
  • Demands: NOW called for equal rights for women, including economic opportunities, fair hiring practices, and equal representation in all aspects of American society. [2, 23, 24, 25, 26]

SCUM Manifesto (1967):
  • Context: Radical feminist Valerie Solanas self-published this controversial and provocative text just before she shot Andy Warhol in 1968.
  • Key Arguments: The manifesto argues that men are biologically inferior and have ruined the world. It suggests forming a group called SCUM (Society for Cutting Up Men) to overthrow society and eliminate the male sex.
  • Controversy and Interpretation: The document was dismissed by many as the ranting of a mentally unstable individual, while others viewed it as a radical satire exposing patriarchal rage. It remains a polarizing text that fueled debates within the women's movement. [27, 28, 29]

Farmworkers' movement
César Chávez's Writings and Speeches:
  • Context: As a leader of the United Farm Workers (UFW), Chávez used nonviolent tactics to organize farmworkers and achieve better working conditions. His speeches and writings functioned as manifestos for the movement.
  • Key Principles:
    • Nonviolence: Chávez advocated for the power of nonviolence and sacrifice, inspired by Martin Luther King Jr. and Mahatma Gandhi.
    • "La Causa": His movement, "The Cause," advocated for union recognition, fair wages, and protection from dangerous pesticides for farmworkers.

  • Influence: Chávez's use of manifestos, speeches, and public statements drew national attention to the plight of farmworkers and rallied support from students, artists, and political figures. [30, 31, 32, 33, 34]


AI responses may include mistakes.


--

Society, Information Technology, and the Global University (2025, forthcoming) 

- Scott GK MacLeod  
Founder, President, CEO & Professor
CC-4 licensed MIT OCW-centric, Wiki, 
World University & School (WUaS) 
- USPS US Post Office, General Delivery, Canyon, CA 94516 


1) non-profit 501(c)(3) Public Charity 
MIT OCW-centric, 
 World University and School - http://worlduniversityandschool.org  

2) for profit general stock company WUaS Corporation in CA - http://worlduniversityandschool.org/AcademicPress.html

(m) 412 478 0116 - sgkmacleod@gmail.com 






* * 


searched on 

'Yoga and dissent 1960s America'

But I also find Yoga meditation unifying too regarding an inner releasing actions and explorations and consciousness.


In 1960s America, yoga became associated with dissent by offering an alternative spiritual and lifestyle path for the counterculture movement, which rejected mainstream institutions. As the counterculture sought to challenge societal norms and authorities, interest grew in Eastern philosophies like yoga, which offered a path to personal consciousness outside of traditional religious structures. Key events like Swami Satchidananda opening the Woodstock festival and the later arrival of influential texts like B.K.S. Iyengar's Light on Yoga cemented yoga's place within the broader movement of dissent. [1, 2, 3, 4, 5]

Yoga as a countercultural and dissenting force
  • Rejection of authority: The counterculture, of which hippies were a part, rejected the "Establishment" and traditional authorities. Yoga provided a practice that was distinctly different from Western institutions, offering an alternative way of living and thinking.
  • Spiritual seeking: Young people were drawn to Eastern philosophies, including yoga, as a way to find meaning and achieve "cosmic consciousness" outside of mainstream religion. Yoga was part of a broader interest in meditation, Eastern mysticism, and personal potential that moved many away from organized religion.
  • Lifestyle and community: Yoga became integrated into the counterculture lifestyle, which included vegetarianism, eco-friendly practices, and intentional communities (communes). For instance, Swami Satchidananda opened the 1969 Woodstock festival, symbolizing the integration of yoga and Eastern spirituality with the counterculture's embrace of peace and love.
  • Influence of key figures:
    • Swami Satchidananda: He founded the Integral Yoga Institute in New York in 1966 and played a prominent role at Woodstock, bringing his teachings to a massive audience.
    • B.K.S. Iyengar: His influential book Light on Yoga was published in the US in 1966, becoming a foundational text for serious practitioners and shaping the practice of yoga for many Americans.
    • Yogi Bhajan: His yoga sessions were a part of the counterculture, with photographs showing him with groups on communes in New Mexico.

  • Broader social context: The growth of yoga interest in the 1960s occurred alongside, and was often intertwined with, other movements that challenged the status quo, such as the Civil Rights Movement, the anti-war movement, and the nascent women's and gay rights movements. Yoga was a part of this larger wave of social and spiritual questioning. [1, 2, 3, 4, 7, 8, 9, 10, 11]


AI responses may include mistakes.


--

Society, Information Technology, and the Global University (2025, forthcoming) 

- Scott GK MacLeod  
Founder, President, CEO & Professor
CC-4 licensed MIT OCW-centric, Wiki, 
World University & School (WUaS) 
- USPS US Post Office, General Delivery, Canyon, CA 94516 


1) non-profit 501(c)(3) Public Charity 
MIT OCW-centric, 
 World University and School - http://worlduniversityandschool.org  

2) for profit general stock company WUaS Corporation in CA - http://worlduniversityandschool.org/AcademicPress.html

(m) 412 478 0116 - sgkmacleod@gmail.com 






* 

But I also find Yoga meditation unifying too regarding an inner releasing actions and explorations and consciousness.





* * * 

I continue to get these AI and Robotics + researchers' academic papers in my email box, compiled by UC Berkeley Prof Anca Dragan (originally from Germany) ... and which related papers will be helpful in developing MIT OCW-centric wiki World University and School's Robotics and Artificial Intelligence and Machine Learning and Large Language Models in all 200 countries and in all 7159 known living languages ... and in a #RealisticVirtualEarth #ForRobotics and #ForEverything ... 


Anca D Dragan
Assistant Professor at UC Berkeley // Director, AI Safety and Alignment, Google DeepMind
Verified email at berkeley.edu - Homepage

https://scholar.google.com/citations?user=UgHB5oAAAAAJ&hl=en


Title
Cited by
Year
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
https://arxiv.org/abs/2403.05530
2766*2024
Gemma 2: Improving open language models at a practical size
G Team, M Riviere, S Pathak, PG Sessa, C Hardin, S Bhupatiraju, ...
arXiv preprint arXiv:2408.00118
13752024
Legibility and predictability of robot motion
AD Dragan, KCT Lee, SS Srinivasa
2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
9812013
Cooperative Inverse Reinforcement Learning
D Hadfield-Menell, A Dragan, P Abbeel, S Russell
Neural Information Processing Systems (NIPS)
9652016
CHOMP: Covariant Hamiltonian Optimization for Motion Planning
M Zucker, N Ratliff, AD Dragan, M Pivtoraiko, M Klingensmith, C Dellin, ...
International Journal of Robotics Research
9572013
Open problems and fundamental limitations of reinforcement learning from human feedback
S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ...
arXiv preprint arXiv:2307.15217
7542023
Planning for autonomous cars that leverage effects on human actions.
D Sadigh, S Sastry, SA Seshia, AD Dragan
Robotics: Science and systems 2, 1-9
6962016
On the utility of learning about humans for human-ai coordination
M Carroll, R Shah, MK Ho, T Griffiths, S Seshia, P Abbeel, A Dragan
Advances in neural information processing systems 32
5892019
Inverse reward design
D Hadfield-Menell, S Milli, P Abbeel, SJ Russell, A Dragan
Advances in neural information processing systems 30
5742017
A policy-blending formalism for shared control
AD Dragan, SS Srinivasa
The International Journal of Robotics Research 32 (7), 790-805
4952013
Active preference-based learning of reward functions
D Sadigh, AD Dragan, S Sastry, S Seshia
RSS
4762017
Effects of robot motion on human-robot collaboration
AD Dragan, S Bauman, J Forlizzi, SS Srinivasa
Proceedings of the tenth annual ACM/IEEE international conference on human …
4362015
Managing extreme AI risks amid rapid progress
Y Bengio, G Hinton, A Yao, D Song, P Abbeel, T Darrell, YN Harari, ...
Science 384 (6698), 842-845
4242024
SQIL: imitation learning via regularized behavioral cloning
S Reddy, AD Dragan, S Levine
arXiv preprint arXiv:1905.11108 2 (5)
414*2019
On stochastic optimal control and reinforcement learning by approximate inference
K Rawlik, M Toussaint, S Vijayakumar
Proceedings of Robotics: Science and Systems VIII
4012012
Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities
G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ...
arXiv preprint arXiv:2507.06261
3822025
Toward seamless human-robot handovers
K Strabala, MK Lee, A Dragan, J Forlizzi, SS Srinivasa, M Cakmak, ...
Journal of Human-Robot Interaction 2 (1), 112-132
3672013
Hierarchical game-theoretic planning for autonomous vehicles
JF Fisac, E Bronstein, E Stefansson, D Sadigh, SS Sastry, AD Dragan
2019 International conference on robotics and automation (ICRA), 9590-9596
3512019
Dart: Noise injection for robust imitation learning
M Laskey, J Lee, R Fox, A Dragan, K Goldberg
Conference on robot learning, 143-156
3292017
Information gathering actions over human internal state
D Sadigh, SS Sastry, SA Seshia, A Dragan
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems …
2602016
Planning for cars that coordinate with people: leveraging effects on human actions for planning and active information gathering over human internal state
D Sadigh, N Landolfi, SS Sastry, SA Seshia, AD Dragan
Autonomous Robots 42 (7), 1405-1426
2532018
Reward-rational (implicit) choice: A unifying formalism for reward learning
HJ Jeon, S Milli, A Dragan
Advances in Neural Information Processing Systems 33, 4415-4426
2472020
The social cost of strategic classification
S Milli, J Miller, AD Dragan, M Hardt
Proceedings of the conference on fairness, accountability, and transparency …
2452019
Do you want your autonomous car to drive like you?
C Basu, Q Yang, D Hungerman, M Singhal, AD Dragan
Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot …
2422017
Efficient iterative linear-quadratic approximations for nonlinear multi-player general-sum differential games
D Fridovich-Keil, E Ratner, L Peters, AD Dragan, CJ Tomlin
2020 IEEE international conference on robotics and automation (ICRA), 1475-1481
2412020
Generating legible motion
A Dragan, S Srinivasa
Carnegie Mellon University
2412013
Model reconstruction from model explanations
S Milli, L Schmidt, AD Dragan, M Hardt
Proceedings of the Conference on Fairness, Accountability, and Transparency, 1-9
2402019
The off-switch game
D Hadfield-Menell, A Dragan, P Abbeel, S Russell
IJCAI
2392017
Shared autonomy via deep reinforcement learning
S Reddy, AD Dragan, S Levine
arXiv preprint arXiv:1802.01744
2352018
Automatically auditing large language models via discrete optimization
E Jones, A Dragan, A Raghunathan, J Steinhardt
International Conference on Machine Learning, 15307-15329
2222023
Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2
T Lieberum, S Rajamanoharan, A Conmy, L Smith, N Sonnerat, V Varma, ...
arXiv preprint arXiv:2408.05147
2122024
Enabling Robots to Communicate their Objectives
SH Huang, D Held, P Abbeel, AD Dragan
RSS
2072017
Learning robot objectives from physical human interaction
A Bajcsy, DP Losey, MK O’malley, AD Dragan
Conference on robot learning, 217-226
2022017
Formalizing assistive teleoperation
AD Dragan, SS Srinivasa
Robotics: Science and Systems
1992012
Probabilistically safe robot planning with confidence-based human predictions
JF Fisac, A Bajcsy, SL Herbert, D Fridovich-Keil, S Wang, CJ Tomlin, ...
arXiv preprint arXiv:1806.00109
1782018
Confidence-aware motion prediction for real-time collision avoidance1
D Fridovich-Keil, A Bajcsy, JF Fisac, SL Herbert, S Wang, AD Dragan, ...
The International Journal of Robotics Research 39 (2-3), 250-265
1772020
Expressing robot incapability
M Kwon, SH Huang, AD Dragan
Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot …
1772018
Establishing appropriate trust via critical states
SH Huang, K Bhatia, P Abbeel, AD Dragan
2018 IEEE/RSJ international conference on intelligent robots and systems …
1722018
Herb 2.0: Lessons learned from developing a mobile manipulator for the home
SS Srinivasa, D Berenson, M Cakmak, A Collet, MR Dogar, AD Dragan, ...
Proceedings of the IEEE 100 (8), 2410-2428
1662012
B-pref: Benchmarking preference-based reinforcement learning
K Lee, L Smith, A Dragan, P Abbeel
arXiv preprint arXiv:2111.03026
1602021
Physics-based grasp planning through clutter
M Dogar, K Hsiao, M Ciocarlie, S Srinivasa
MIT Press 8, 57-64
1602012
Deliberate delays during robot-to-human handovers improve compliance with gaze communication
H Admoni, A Dragan, SS Srinivasa, B Scassellati
Proceedings of the 2014 ACM/IEEE international conference on Human-robot …
1532014
Where do you think you're going?: Inferring beliefs about dynamics from behavior
S Reddy, A Dragan, S Levine
Advances in Neural Information Processing Systems 31
1392018
Learning from physical human corrections, one feature at a time
A Bajcsy, DP Losey, MK O'Malley, AD Dragan
Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot …
1292018
Managing ai risks in an era of rapid progress
Y Bengio, G Hinton, A Yao, D Song, P Abbeel, YN Harari, YQ Zhang, ...
arXiv preprint arXiv:2310.17688, 18
1192023
Pragmatic-pedagogic value alignment
JF Fisac, MA Gates, JB Hamrick, C Liu, D Hadfield-Menell, ...
Robotics research: the 18th international symposium Isrr, 49-57
1112019
Perceived robot capability
E Cha, AD Dragan, SS Srinivasa
2015 24th IEEE International Symposium on Robot and Human Interactive …
1092015
Robot grasping in clutter: Using a hierarchy of supervisors for learning from demonstrations
M Laskey, J Lee, C Chuck, D Gealy, W Hsieh, FT Pokorny, AD Dragan, ...
2016 IEEE international conference on automation science and engineering …
1072016
Shiv: Reducing supervisor burden in dagger using support vectors for efficient learning from demonstrations in high dimensional state spaces
M Laskey, S Staszak, WYS Hsieh, J Mahler, FT Pokorny, AD Dragan, ...
2016 IEEE International Conference on Robotics and Automation (ICRA), 462-469
1062016
Courteous autonomous cars
L Sun, W Zhan, M Tomizuka, AD Dragan
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …
1052018
Integrating human observer inferences into robot motion planning
A Dragan, S Srinivasa
Autonomous Robots 37 (4), 351-368
1052014
Manipulation planning with goal sets using constrained trajectory optimization
AD Dragan, ND Ratliff, SS Srinivasa
2011 IEEE International Conference on Robotics and Automation, 4582-4588
1002011
A scalable framework for real-time multi-robot, multi-human collision avoidance
A Bajcsy, SL Herbert, D Fridovich-Keil, JF Fisac, S Deglurkar, AD Dragan, ...
2019 international conference on robotics and automation (ICRA), 936-943
992019
Learning human objectives by evaluating hypothetical behavior
S Reddy, A Dragan, S Levine, S Legg, J Leike
International conference on machine learning, 8020-8029
982020
Learning a prior over intent via meta-inverse reinforcement learning
K Xu, E Ratner, A Dragan, S Levine, C Finn
International conference on machine learning, 6952-6962
912019
Legible robot pointing
RM Holladay, AD Dragan, SS Srinivasa
The 23rd IEEE International Symposium on robot and human interactive …
912014
Evaluating frontier models for dangerous capabilities
M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ...
arXiv preprint arXiv:2403.13793
902024
Should Robots be Obedient?
S Milli, D Hadfield-Menell, A Dragan, S Russell
IJCAI
892017
Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations
M Laskey, C Chuck, J Lee, J Mahler, S Krishnan, K Jamieson, A Dragan, ...
ICRA
872016
On the feasibility of learning, rather than assuming, human biases for reward inference
R Shah, N Gundotra, P Abbeel, A Dragan
International conference on machine learning, 5670-5679
852019
Goal inference improves objective and perceived performance in human-robot collaboration
C Liu, JB Hamrick, JF Fisac, AD Dragan, JK Hedrick, SS Sastry, ...
arXiv preprint arXiv:1802.01780
852018
Benchmarks and algorithms for offline preference-based reward learning
D Shin, AD Dragan, DS Brown
arXiv preprint arXiv:2301.01392
842023
Functional gradient motion planning in reproducing kernel hilbert spaces
Z Marinho, A Dragan, A Byravan, B Boots, S Srinivasa, G Gordon
arXiv preprint arXiv:1601.03648
792016
Learning the communication of intent prior to physical collaboration
K Strabala, MK Lee, A Dragan, J Forlizzi, SS Srinivasa
2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human …
782012
Safety assurances for human-robot interaction via confidence-aware game-theoretic human models
R Tian, L Sun, A Bajcsy, M Tomizuka, AD Dragan
2022 International Conference on Robotics and Automation (ICRA), 11229-11235
772022
Preferences implicit in the state of the world
R Shah, D Krasheninnikov, J Alexander, P Abbeel, A Dragan
arXiv preprint arXiv:1902.04198
772019
Movement primitives via optimization
AD Dragan, K Muelling, JA Bagnell, SS Srinivasa
2015 IEEE International Conference on Robotics and Automation (ICRA), 2339-2346
762015
Less is more: Rethinking probabilistic models of human behavior
A Bobu, DRR Scobee, JF Fisac, SS Sastry, AD Dragan
Proceedings of the 2020 acm/ieee international conference on human-robot …
752020
Expressive robot motion timing
A Zhou, D Hadfield-Menell, A Nagabandi, AD Dragan
Proceedings of the 2017 ACM/IEEE international conference on human-robot …
742017
Imagen 3
J Baldridge, J Bauer, M Bhutani, N Brichtova, A Bunner, L Castrejon, ...
arXiv preprint arXiv:2408.07009
732024
Engagement, user satisfaction, and the amplification of divisive content on social media
S Milli, M Carroll, Y Wang, S Pandey, S Zhao, AD Dragan
PNAS nexus 4 (3), pgaf062
722025
Familiarization to robot motion
A Dragan, S Srinivasa
Proceedings of the 2014 ACM/IEEE international conference on Human-robot …
712014
Accelerating human learning with deep reinforcement learning
S Reddy, S Levine, A Dragan
NIPS workshop: teaching machines, robots, and humans 9, 5-9
702017
Confronting reward model overoptimization with constrained rlhf
T Moskovitz, AK Singh, DJ Strouse, T Sandholm, R Salakhutdinov, ...
arXiv preprint arXiv:2310.04373
692023
On the utility of model learning in hri
R Choudhury, G Swamy, D Hadfield-Menell, AD Dragan
2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
692019
Learning to model the world with language
J Lin, Y Du, O Watkins, D Hafner, P Abbeel, D Klein, A Dragan
arXiv preprint arXiv:2308.01399
682023
Learning from richer human guidance: Augmenting comparison-based learning with feature queries
C Basu, M Singhal, AD Dragan
Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot …
682018
Causal confusion and reward misidentification in preference-based reward learning
J Tien, JZY He, Z Erickson, AD Dragan, DS Brown
arXiv preprint arXiv:2204.06601
662022
Physical interaction as communication: Learning robot objectives online from human corrections
DP Losey, A Bajcsy, MK O’Malley, AD Dragan
The International Journal of Robotics Research 41 (1), 20-44
662022
Estimating and penalizing induced preference shifts in recommender systems
MD Carroll, A Dragan, S Russell, D Hadfield-Menell
International Conference on Machine Learning, 2686-2708
632022
Inferring rewards from language in context
J Lin, D Fried, D Klein, A Dragan
arXiv preprint arXiv:2204.02515
632022
Feature expansive reward learning: Rethinking human input
A Bobu, M Wiggert, C Tomlin, AD Dragan
Proceedings of the 2021 ACM/IEEE international conference on human-robot …
622021
Scaled autonomy: Enabling human operators to control robot fleets
G Swamy, S Reddy, S Levine, AD Dragan
2020 IEEE International Conference on Robotics and Automation (ICRA), 5942-5948
622020
Translating Neuralese
J Andreas, A Dragan, D Klein
ACL
612017
The assistive multi-armed bandit
L Chan, D Hadfield-Menell, S Srinivasa, A Dragan
2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
602019
Teleoperation with intelligent and customizable interfaces
AD Dragan, SS Srinivasa, KCT Lee
Journal of Human-Robot Interaction 2 (2), 33-57
602013
Value alignment verification
DS Brown, J Schneider, A Dragan, S Niekum
International Conference on Machine Learning, 1105-1115
592021
Quantifying hypothesis space misspecification in learning from human–robot demonstrations and physical corrections
A Bobu, A Bajcsy, JF Fisac, S Deglurkar, AD Dragan
IEEE Transactions on Robotics 36 (3), 835-854
592020
Learning from experience in manipulation planning: Setting the right goals
AD Dragan, GJ Gordon, SS Srinivasa
ISRR, 309-326
59*2012
Ave: Assistance via empowerment
Y Du, S Tiomkin, E Kiciman, D Polani, P Abbeel, A Dragan
Advances in Neural Information Processing Systems 33, 4560-4571
552020
Deceptive robot motion: synthesis, analysis and experiments
A Dragan, R Holladay, S Srinivasa
Autonomous Robots 39 (3), 331-345
552015
An Analysis of Deceptive Robot Motion
AD Dragan, R Holladay, SS Srinivasa
Robotics Science and Systems
552014
Robot planning with mathematical models of human state and action
AD Dragan
arXiv preprint arXiv:1705.04226
522017
Simplifying reward design through divide-and-conquer
E Ratner, D Hadfield-Menell, AD Dragan
arXiv preprint arXiv:1806.02501
502018
Implicitly assisting humans to choose good grasps in robot to human handovers
A Bestick, R Bajcsy, AD Dragan
International symposium on experimental robotics, 341-354
482016
The effect of modeling human rationality level on learning rewards from multiple feedback types
GR Ghosal, M Zurek, DS Brown, AD Dragan
Proceedings of the AAAI Conference on Artificial Intelligence 37 (5), 5983-5992
472023
The boltzmann policy distribution: Accounting for systematic suboptimality in human models
C Laidlaw, A Dragan
arXiv preprint arXiv:2204.10759
472022
Inducing structure in reward learning by learning features
A Bobu, M Wiggert, C Tomlin, AD Dragan
The International Journal of Robotics Research 41 (5), 497-518
472022
A hamilton-jacobi reachability-based framework for predicting and analyzing human motion for safe planning
S Bansal, A Bajcsy, E Ratner, AD Dragan, CJ Tomlin
2020 IEEE International Conference on Robotics and Automation (ICRA), 7149-7155
472020
Generating plans that predict themselves
JF Fisac, C Liu, JB Hamrick, S Sastry, JK Hedrick, TL Griffiths, AD Dragan
Algorithmic Foundations of Robotics XII: Proceedings of the Twelfth Workshop …
472020
An efficient, generalized bellman update for cooperative inverse reinforcement learning
D Malik, M Palaniappan, J Fisac, D Hadfield-Menell, S Russell, A Dragan
International Conference on Machine Learning, 3394-3402
462018
Learning human ergonomic preferences for handovers
A Bestick, R Pandya, R Bajcsy, AD Dragan
2018 IEEE international conference on robotics and automation (ICRA), 3257-3264
462018
Active comparison based learning incorporating user uncertainty and noise
R Holladay, S Javdani, A Dragan, S Srinivasa
RSS Workshop on Model Learning for Human-Robot Communication
462016
Viewpoint-based legibility optimization
S Nikolaidis, A Dragan, S Srinivasa
Human-Robot Interaction (HRI), 2016 11th ACM/IEEE International Conference …
46*2016
Evaluating the robustness of collaborative agents
P Knott, M Carroll, S Devlin, K Ciosek, K Hofmann, AD Dragan, R Shah
arXiv preprint arXiv:2101.05507
452021
Learning under misspecified objective spaces
A Bobu, A Bajcsy, JF Fisac, AD Dragan
Conference on robot learning, 796-805
452018
Uni [mask]: Unified inference in sequential decision problems
M Carroll, O Paradise, J Lin, R Georgescu, M Sun, D Bignell, S Milani, ...
Advances in neural information processing systems 35, 35365-35378
432022
Benefits of assistance over reward learning
R Shah, P Freire, N Alex, R Freedman, D Krasheninnikov, L Chan, ...
402020
Bridging rl theory and practice with the effective horizon
C Laidlaw, SJ Russell, A Dragan
Advances in Neural Information Processing Systems 36, 58953-59007
392023
Goal representations for instruction following: A semi-supervised language interface to control
V Myers, AW He, K Fang, HR Walke, P Hansen-Estruch, CA Cheng, ...
Conference on Robot Learning, 3894-3908
392023
Learning representations that enable generalization in assistive tasks
JZY He, Z Erickson, DS Brown, A Raghunathan, A Dragan
Conference on Robot Learning, 2105-2114
392023
Situational confidence assistance for lifelong shared autonomy
M Zurek, A Bobu, DS Brown, AD Dragan
2021 IEEE International Conference on Robotics and Automation (ICRA), 2783-2789
372021
A robust control framework for human motion prediction
A Bajcsy, S Bansal, E Ratner, CJ Tomlin, AD Dragan
IEEE Robotics and Automation Letters 6 (1), 24-31
372020
Inferring and assisting with constraints in shared autonomy
N Mehr, R Horowitz, AD Dragan
2016 IEEE 55th Conference on Decision and Control (CDC), 6689-6696
362016
Ai alignment with changing and influenceable reward functions
M Carroll, D Foote, A Siththaranjan, S Russell, A Dragan
arXiv preprint arXiv:2405.17713
352024
Aligning robot and human representations
A Bobu, A Peng, P Agrawal, J Shah, AD Dragan
arXiv preprint arXiv:2302.01928
352023
Learning to influence human behavior with offline reinforcement learning
J Hong, S Levine, A Dragan
Advances in neural information processing systems 36, 36094-36105
342023
Twitter's algorithm: Amplifying anger, animosity, and affective polarization
S Milli, M Carroll, S Pandey, Y Wang, AD Dragan
CoRR
342023
Explainable robotic systems
MMA De Graaf, BF Malle, A Dragan, T Ziemke
Companion of the 2018 ACM/IEEE International Conference on Human-Robot …
332018
Zero-shot goal-directed dialogue via rl on imagined conversations
J Hong, S Levine, A Dragan
arXiv preprint arXiv:2311.05584
322023
Human irrationality: both bad and good for reward inference
L Chan, A Critch, A Dragan
arXiv preprint arXiv:2111.06956
322021
Policy gradient bayesian robust optimization for imitation learning
Z Javed, DS Brown, S Sharma, J Zhu, A Balakrishna, M Petrik, A Dragan, ...
International Conference on Machine Learning, 4785-4796
312021
An approach to technical agi safety and security
R Shah, A Irpan, AM Turner, A Wang, A Conmy, D Lindner, ...
arXiv preprint arXiv:2504.01849
302025
First contact: Unsupervised human-machine co-adaptation via mutual information maximization
S Reddy, S Levine, A Dragan
Advances in Neural Information Processing Systems 35, 31542-31556
302022
Estimating and penalizing preference shift in recommender systems
M Carroll, D Hadfield-Menell, S Russell, A Dragan
Proceedings of the 15th ACM Conference on Recommender Systems, 661-667
302021
Aligning human and robot representations
A Bobu, A Peng, P Agrawal, JA Shah, AD Dragan
Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot …
292024
Towards modeling and influencing the dynamics of human learning
R Tian, M Tomizuka, AD Dragan, A Bajcsy
Proceedings of the 2023 ACM/IEEE international conference on human-robot …
292023
On the sensitivity of reward inference to misspecified human models
J Hong, K Bhatia, A Dragan
arXiv preprint arXiv:2212.04717
292022
Analyzing human models that adapt online
A Bajcsy, A Siththaranjan, CJ Tomlin, AD Dragan
2021 IEEE International Conference on Robotics and Automation (ICRA), 2754-2760
292021
Optimal cost design for model predictive control
A Jain, L Chan, DS Brown, AD Dragan
Learning for Dynamics and Control, 1205-1217
292021
Variational Bayesian optimization for runtime risk-sensitive control
S Kuindersma, R Grupen, A Barto
Robotics: Science and systems viii, 201-208
292012
Sirl: Similarity-based implicit representation learning
A Bobu, Y Liu, R Shah, DS Brown, AD Dragan
Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot …
282023
Control for Societal-Scale Challenges: Roadmap 2030
A Alleyne, F Allgöwer, AD Ames, S Amin, J Anderson, AM Annaswamy, ...
IEEE Control Systems Society Publication
282023
The MineRL BASALT competition on learning from human feedback
R Shah, C Wild, SH Wang, N Alex, B Houghton, W Guss, S Mohanty, ...
arXiv preprint arXiv:2107.01969
282021
Exploiting passive dynamics with variable stiffness actuation in robot brachiation
J Nakanishi, S Vijayakumar
Robotics: Science and systems 8, 305
282013
On targeted manipulation and deception when optimizing llms for user feedback
M Williams, M Carroll, A Narang, C Weisser, B Murphy, A Dragan
arXiv preprint arXiv:2411.02306
272024
Learning temporal distances: Contrastive successor features can provide a metric structure for decision-making
V Myers, C Zheng, A Dragan, S Levine, B Eysenbach
arXiv preprint arXiv:2406.17098
272024
Asha: Assistive teleoperation via human-in-the-loop reinforcement learning
S Chen, J Gao, S Reddy, G Berseth, AD Dragan, S Levine
2022 International Conference on Robotics and Automation (ICRA), 7505-7512
262022
Literal or pedagogic human? analyzing human model misspecification in objective learning
S Milli, AD Dragan
Uncertainty in artificial intelligence, 925-934
262020
Cost functions for robot motion style
A Zhou, AD Dragan
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …
262018
Special issue on learning for human–robot collaboration
L Rozo, HB Amor, S Calinon, A Dragan, D Lee
Autonomous Robots 42 (5), 953-956
262018
Online customization of teleoperation interfaces
AD Dragan, SS Srinivasa
2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human …
262012
Toward grounded commonsense reasoning
M Kwon, H Hu, V Myers, S Karamcheti, A Dragan, D Sadigh
2024 IEEE International Conference on Robotics and Automation (ICRA), 5463-5470
252024
Offline preference-based apprenticeship learning
D Shin, DS Brown, AD Dragan
arXiv preprint arXiv:2107.09251
242021
On complementing end-to-end human behavior predictors with planning
L Sun, X Jia, AD Dragan
arXiv preprint arXiv:2103.05661
232021
Choice set misspecification in reward inference
R Freedman, R Shah, A Dragan
arXiv preprint arXiv:2101.07691
232021
Legible robot motion planning
AD Dragan
Carnegie Mellon University
232015
Chain of thought monitorability: A new and fragile opportunity for ai safety
T Korbak, M Balesni, E Barnes, Y Bengio, J Benton, J Bloom, M Chen, ...
arXiv preprint arXiv:2507.11473
212025
Assisted perception: optimizing observations to communicate state
S Reddy, S Levine, A Dragan
Conference on robot learning, 748-764
212021
Nonverbal robot feedback for human teachers
SH Huang, I Huang, R Pandya, AD Dragan
arXiv preprint arXiv:1911.02320
212019
Assitive Teleoperation for Manipulation Tasks
AD Dragan, SS Srinivasa
202012
Preventing reward hacking with occupancy measure regularization
C Laidlaw, S Singhal, A Dragan
182023
Toward grounded social reasoning
M Kwon, H Hu, V Myers, S Karamcheti, A Dragan, D Sadigh
arXiv preprint arXiv:2306.08651
182023
Pragmatic image compression for human-in-the-loop decision-making
S Reddy, A Dragan, S Levine
Advances in Neural Information Processing Systems 34, 26499-26510
182021
Adversaries can misuse combinations of safe models
E Jones, A Dragan, J Steinhardt
arXiv preprint arXiv:2406.14595
172024
Correlated proxies: A new definition and improved mitigation for reward hacking
C Laidlaw, S Singhal, A Dragan
arXiv preprint arXiv:2403.03185
172024
Optimal behavior prior: Data-efficient human models for improved human-ai collaboration
M Yang, M Carroll, A Dragan
arXiv preprint arXiv:2211.01602
172022
Teaching robots to span the space of functional expressive motion
A Sripathy, A Bobu, Z Li, K Sreenath, DS Brown, AD Dragan
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems …
172022
Preference learning along multiple criteria: A game-theoretic perspective
K Bhatia, A Pananjady, P Bartlett, A Dragan, MJ Wainwright
Advances in neural information processing systems 33, 7413-7424
172020
Learning from extrapolated corrections
JY Zhang, AD Dragan
2019 International Conference on Robotics and Automation (ICRA), 7034-7040
172019
Social cohesion in autonomous driving
NC Landolfi, AD Dragan
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …
172018
Assisted robust reward design
JZY He, AD Dragan
arXiv preprint arXiv:2111.09884
162021
How to be helpful to multiple people at once
V Gates, TL Griffiths, AD Dragan
Cognitive science 44 (6), e12841
162020
Learning optimal advantage from preferences and mistaking it for reward
WB Knox, S Hatgis-Kessell, SO Adalgeirsson, S Booth, A Dragan, P Stone, ...
Proceedings of the AAAI Conference on Artificial Intelligence 38 (9), 10066 …
152024
A study of causal confusion in preference-based reward learning
J Tien, JZY He, Z Erickson, A Dragan, DS Brown
ICML 2022: Workshop on Spurious Correlations, Invariance and Stability
152022
Human-AI learning performance in multi-armed bandits
R Pandya, SH Huang, D Hadfield-Menell, AD Dragan
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 369-375
152019
Trajectory improvement and reward learning from comparative language feedback
Z Yang, M Jun, J Tien, SJ Russell, A Dragan, E Bıyık
arXiv preprint arXiv:2410.06401
142024
Explaining robot policies
O Watkins, S Huang, J Frost, K Bhatia, E Weiner, P Abbeel, T Darrell, ...
Applied AI Letters 2 (4), e52
132021
Experiments with Balancing on Irregular Terrains using the Dreamer Mobile Humanoid Robot.
L Sentis, J Petersen, R Philippsen
Robotics: Science and Systems
132012
Introduction to the special issue on explainable robotic systems
MMA De Graaf, A Dragan, BF Malle, T Ziemke
ACM Transactions on Human-Robot Interaction (THRI) 10 (3), 1-4
122021
X2T: Training an x-to-text typing interface with online learning from user feedback
J Gao, S Reddy, G Berseth, N Hardy, N Natraj, K Ganguly, AD Dragan, ...
arXiv preprint arXiv:2203.02072
112022
Effects of robot capability on user acceptance
E Cha, AD Dragan, SS Srinivasa
2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
112013
Cos: Enhancing personalization and mitigating bias with context steering
JZY He, S Pandey, ML Schrum, A Dragan
arXiv preprint arXiv:2405.01768
102024
Dynamically switching human prediction models for efficient planning
A Sripathy, A Bobu, DS Brown, AD Dragan
2021 IEEE International Conference on Robotics and Automation (ICRA), 3495-3501
102021
Bayesian robustness: A nonasymptotic viewpoint
K Bhatia, YA Ma, AD Dragan, PL Bartlett, MI Jordan
arXiv preprint arXiv:1907.11826
102019
Feature-based prediction of trajectories for socially compliant navigation
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
102013
When your ais deceive you: Challenges with partial observability of human evaluators in reward learning
L Lang, D Foote, S Russell, AD Dragan, E Jenner, S Emmons
CoRR
92024
Configuration space metrics
HJ Jeon, AD Dragan
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …
92018
Collaborative manipulation: new challenges for robotics and hri
AD Dragan, AL Thomaz, SS Srinivasa
2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
92013
Distributed Approximation of Joint Measurement Distributions Using Mixtures of Gaussians.
BJ Julian, SL Smith, D Rus
Robotics: Science and Systems
92012
Q-sft: Q-learning for language models via supervised fine-tuning
J Hong, A Dragan, S Levine
arXiv preprint arXiv:2411.05193
82024
Towards flexible inference in sequential decision problems via bidirectional transformers
M Carroll, J Lin, O Paradise, R Georgescu, M Sun, D Bignell, S Milani, ...
arXiv preprint arXiv:2204.13326
82022
Learning what to do by simulating the past
D Lindner, R Shah, P Abbeel, A Dragan
arXiv preprint arXiv:2104.03946
82021
Learning to assist humans without inferring rewards
V Myers, E Ellis, S Levine, B Eysenbach, A Dragan
Advances in Neural Information Processing Systems 37, 71540-71567
72024
Offline rl with observation histories: Analyzing and improving sample complexity
J Hong, A Dragan, S Levine
arXiv preprint arXiv:2310.20663
72023
Time-efficient reward learning via visually assisted cluster ranking
D Zhang, M Carroll, A Bobu, A Dragan
arXiv preprint arXiv:2212.00169
72022
On complementing end-to-end human motion predictors with planning
L Sun, X Jia, AD Dragan
2021 Robotics: Science and Systems (RSS)
72021
Effects of speech on perceived capability
E Cha, A Dragan, J Forlizzi, S Srinivasa
Proceedings of the 2014 ACM/IEEE international conference on Human-robot …
72014
When your AIs deceive you: Challenges of partial observability in reinforcement learning from human feedback
L Lang, D Foote, SJ Russell, A Dragan, E Jenner, S Emmons
Advances in Neural Information Processing Systems 37, 93240-93299
62024
A generalized acquisition function for preference-based reward learning
E Ellis, GR Ghosal, SJ Russell, A Dragan, E Bıyık
2024 IEEE International Conference on Robotics and Automation (ICRA), 2814-2821
62024
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
C Laidlaw, B Zhu, S Russell, A Dragan
arXiv preprint arXiv:2312.08369
62023
Efficient cooperative inverse reinforcement learning
M Palaniappan, D Malik, D Hadfield-Menell, A Dragan, S Russell
Proc. ICML Workshop on Reliable Machine Learning in the Wild
62017
Bayesian robustness: A nonasymptotic viewpoint
K Bhatia, YA Ma, AD Dragan, PL Bartlett, MI Jordan
Journal of the American Statistical Association 119 (546), 1112-1123
52024
Scalably solving assistance games
C Laidlaw, E Bronstein, T Guo, D Feng, L Berglund, J Svegliato, S Russell, ...
ICLR 2025 Workshop on Bidirectional Human-AI Alignment
52024
Defining deception in decision making
M Abdulhai, M Carroll, J Svegliato, A Shrivastava, A Dragan, S Levine
42024
Context steering: Controllable personalization at inference time
JZY He, S Pandey, ML Schrum, A Dragan
arXiv preprint arXiv:2405.01768
42024
Optimizing robot behavior via comparative language feedback
J Tien, Z Yang, M Jun, SJ Russell, A Dragan, E Bıyık
Proceedings of the 16th International Conference on Social Robotics (ICSR …
42024
Contextual reliability: When different features matter in different contexts
GR Ghosal, A Setlur, DS Brown, A Dragan, A Raghunathan
International Conference on Machine Learning, 11300-11320
42023
On the utility of model learning in hri
G Swamy, J Schulz, R Choudhury, D Hadfield-Menell, A Dragan
arXiv preprint arXiv:1901.01291
42019
Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
V Myers, BC Zheng, A Dragan, K Fang, S Levine
arXiv preprint arXiv:2502.05454
32025
Interactive dialogue agents via reinforcement learning on hindsight regenerations
J Hong, J Lin, A Dragan, S Levine
arXiv preprint arXiv:2411.05194
32024
Efficient Dynamics Estimation With Adaptive Model Sets
E Ratner, A Bajcsy, T Fong, CJ Tomlin, AD Dragan
IEEE robotics and automation letters 6 (2), 2373-2380
32021
Leveraging critical states to develop trust
SH Huang, K Bhatia, P Abbeel, AD Dragan
RSS 2017 Workshop: Morality and Social Trust in Autonomous Robots
32017
Pre-school children's first encounter with a robot
E Cha, A Dragan, S Srinivasa
Proceedings of the 2014 ACM/IEEE international conference on Human-robot …
32014
Extrinsic calibration from per-sensor egomotion
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
32013
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
M Pan, M Schrum, V Myers, E Bıyık, A Dragan
arXiv preprint arXiv:2406.06714
22024
Scalable oversight by accounting for unreliable feedback
S Singhal, C Laidlaw, A Dragan
ICML 2024 Workshop on Models of Human Feedback for AI Alignment
22024
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
J Gao, S Reddy, G Berseth, AD Dragan, S Levine
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems …
22023
Video-guided skill discovery
M Tomar, D Ghosh, V Myers, A Dragan, ME Taylor, P Bachman, S Levine
ICML 2023 Workshop The Many Facets of Preference-Based Learning
22023
Agnostic learning with unknown utilities
K Bhatia, PL Bartlett, AD Dragan, J Steinhardt
arXiv preprint arXiv:2104.08482
22021
Irrationality can help reward inference
L Chan, A Critch, A Dragan
22019
Few-shot intent inference via meta-inverse reinforcement learning
K Xu, E Ratner, A Dragan, S Levine, C Finn
22018
Inferring reward functions from demonstrators with unknown biases
R Shah, N Gundotra, P Abbeel, A Dragan
22018
Assistive teleoperation: A new domain for interactive learning
A Dragan, S Srinivasa
AAAI fall symposium on robots interactively learning from human teachers, 1-4
22012
AssistanceZero: Scalably Solving Assistance Games
C Laidlaw, E Bronstein, T Guo, D Feng, L Berglund, J Svegliato, S Russell, ...
arXiv preprint arXiv:2504.07091
12025
Cos: Enhancing personalization and mitigating bias with context steering
S Pandey, JZY He, ML Schrum, A Dragan
Neurips Safe Generative AI Workshop 2024
12024
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier
JZY He, DS Brown, Z Erickson, A Dragan
Conference on Robot Learning, 1865-1886
12023
Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media Emilie Flamme
S Milli, M Carroll, Y Wang, S Pandey, S Zhao, A Dragan
12023
Enabling Generalization of Human Models for Human-AI Collaboration to New Tasks
X Yang, A Dragan
Master’s thesis. EECS Department, University of California, Berkeley. http …
12021
Xt2: Training an x-to-text typing interface with online learning from implicit feedback
J Gao, S Reddy, G Berseth, AD Dragan, S Levine
International Conference on Learning Representations (ICLR)
12021
An extensible interactive interface for agent design
M Rahtz, J Fang, AD Dragan, D Hadfield-Menell
arXiv preprint arXiv:1906.02641
12019
Specifying AI Objectives as a Human-AI Collaboration problem
A Dragan
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 329-329
12019
Towards Persistent Localization and Mapping with a Continuous Appearance-Based Topology
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
12013
Parsing Indoor Scenes Using RGB-D Imager
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
12013
Recognition, Prediction, and Planning for Assisted Teleoperation of Freeform Tasks
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
12013
Learning to provide better examples for our robots
A Dragan, S Srinivasa
Carnegie Mellon University
12011
A Theoretical Explanation of Deep RL Performance in Stochastic Environments
C Laidlaw, B Zhu, S Russell, A Dragan
NeurIPS 2023 Workshop on Generalization in Planning
1
The impacts of known and unknown demonstrator irrationality on reward inference
L Chan, A Critch, A Dragan
1
What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning
S Reddy, AD Dragan, S Levine
1
Can AI Mediation Improve Democratic Deliberation? Sébastien A. Krier using Midjourney 6.1
MH Tessler, G Evans, MA Bakker, I Gabriel, S Bridgers, R Jain, R Koster, ...
Artificial Intelligence
2025
Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
J Hong, A Dragan, S Levine
arXiv preprint arXiv:2505.18098
2025
Achieving AI Alignment with Unreliable Supervision
S Singhal, C Laidlaw, A Dragan
2024
Preventing Reward Hacking with Occupancy Measure Regularization
S Singhal, C Laidlaw, A Dragan
2024
Context Steering: Controllable Personalization at Inference Time
J Zhi-Yang He, S Pandey, ML Schrum, A Dragan
arXiv e-prints, arXiv: 2405.01768
2024
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier
J Zhi-Yang He, Z Erickson, DS Brown, AD Dragan
arXiv e-prints, arXiv: 2310.10610
2023
Collaborative Research: HCC: Medium: Aligning Robot Representations with Humans
A Dragan
NSF Award Number 2310757. Directorate for Computer and Information Science …
2023
Similarity-Based Representation Learning
Y Liu, A Bobu, A Dragan
2023
Learning Representations that Enable Generalization in Assistive Tasks
J Zhi-Yang He, A Raghunathan, DS Brown, Z Erickson, AD Dragan
arXiv e-prints, arXiv: 2212.03175
2022
Implicit Communication in Human-Machine Collaboration
A Dragan
2022
Inducing Structure in Reward Learning by Learning
A Bobu, M Wiggert, C Tomlin, A Dragan
2021
Assisted Robust Reward Design
J Zhi-Yang He, AD Dragan
arXiv e-prints, arXiv: 2111.09884
2021
Analyzing Human Models that Adapt Online
A Sripathy, A Bobu, D Brown, A Dragan
IEEE International Conference on Robotics and Automation
2021
Explainable Robotic Systems: Introduction to the special issue
M DE GRAAF, A DRAGAN, BF MALLE, TOM ZIEMKE
2021
Project Plan: Benchmarking Representation Learning for Imitation Learning
X Chen, S Toyer, C Wild, N Alex, BS Emmons, S Wang, S Russell, ...
2020
Learning with Humans in the Loop
G Swamy, A Dragan, S Levine
2020
Comparing Game Planners
S Luo, A Dragan
2020
Learning from Intended Corrections
JY Zhang, AD Dragan
CoRR
2018
The Off-Switch Game: Incentives for Allowing AI Shutdown
D Hadfield-Menell, A Dragan, P Abbeel, S Russell
< bound method Organization. get_name_with_acronym of< Organization …
2017
CAREER: Towards Autonomously Generating Robot Behavior for Coordination with Humans-Accounting for Effects on Human Actions
A Dragan
NSF Award Number 1652083. Directorate for Computer and Information Science …
2017
Geometric Mechanics for Continuous Swimmers on Granular Material
J Dai, H Faraji, P Schiebel, C Gong, M Travers, R Hatton, D Goldman, ...
APS March Meeting Abstracts 2016, V40. 004
2016
Publication Submission Form
TW Fong, J Scholtz, J Shah, L Flueckiger, C Kunz, D Lees, J Schreiner, ...
Journal Article 30 (3), 705-718
2014
Legible user input for intent prediction
KCT Lee, AD Dragan, SS Srinivasa
2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI …
2013
Distributed Approximation of Joint Measurement Distributions Using Mixtures of Gaussians
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Visual Route Recognition with a Handful of Bits
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Contextual Sequence Prediction with Application to Control Library Optimization
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Failure Anticipation in Pursuit-Evasion
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Real-Time Inverse Dynamics Learning for Musculoskeletal Robots Based on Echo State Gaussian Process Regression
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
What's in the Bag: A Distributed Approach to 3D Shape Duplication with Modular Robots
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
E-Graphs: Bootstrapping Planning with Experience Graphs
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Optimal Control with Weighted Average Costs and Temporal Logic Specifications
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Towards A Swarm of Agile Micro Quadrotors
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Efficiently Finding Optimal Winding-Constrained Loops in the Plane
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Affine Trajectory Deformation for Redundant Manipulators
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Hierarchical Motion Planning in Topological Representations
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Reducing Conservativeness in Safety Guarantees by Learning Disturbances Online: Iterated Guaranteed Safe Online Learning
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Probabilistic Temporal Logic for Motion Planning with Resource Threshold Constraints
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Time-Optimal Trajectory Generation for Path Following with Bounded Acceleration and Velocity
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Nonparametric Bayesian Models for Unsupervised Scene Analysis and Reconstruction
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Minimal Coordinate Formulation of Contact Dynamics in Operational Space
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Inference on Networks of Mixtures for Robust Robot Mapping
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Robust Object Grasping Using Force Compliant Motion Primitives
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
FFT-Based Terrain Segmentation for Underwater Mapping
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Robust Navigation Execution by Planning in Belief Space
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Development of a Testbed for Robotic Neuromuscular Controllers
P Agarwal, S Kumar, J Ryde, J Corso, V Krovi, N Ahmed, J Schoenberg, ...
MIT Press
2013
Publication Submission Form
TD Niemueller, G Lakemeyer, S Srinivasa, D Berenson, M Cakmak, ...
Journal Article 100 (8), 2410-2428
2012
The Effective Horizon Challenge
C Laidlaw, D Khalil, M Li, L Newhouse, S Russell, A Dragan
The Exploration in AI Today Workshop at ICML 2025
CTRL-Rec: Controlling Recommender Systems With Natural Language
M Carroll, A Foote, M Williams, A Dragan, WB Knox, S Milli
ICLR 2025 Workshop on Bidirectional Human-AI Alignment
Diagnostic Uncertainty: Teaching Language Models to Describe Open-Ended Uncertainty
B Sui, J Lin, M Li, A Dragan, D Klein, J Steinhardt
ICLR 2025 Workshop on Building Trust in Language Models and Applications
Zero-Shot Goal Dialogue via Reinforcement Learning on Imagined Conversations
J Hong, S Levine, A Dragan
Reliability-Aware Preference Learning for LLM Reward Models
S Singhal, C Laidlaw, A Dragan
Targeted Manipulation and Deception Emerge in LLMs Trained on User* Feedback
M Williams, M Carroll, C Weisser, B Murphy, A Narang, A Dragan
Workshop on Socially Responsible Language Modelling Research
Successor Representations Enable Emergent Compositional Instruction Following
V Myers, C Zheng, A Dragan, K Fang, S Levine
CoS: Enhancing Personalization with Context Steering
S Pandey, JZY He, ML Schrum, A Dragan
Workshop on Socially Responsible Language Modelling Research
Learning human-robot collaboration from human feedback
JZY He, A Rai, AD Dragan
RobULA: Efficient Sampling for Robust Bayesian Inference
K Bhatia, YA Ma, AD Dragan, MI Jordan, PL Bartlett
Model-Free Shared Autonomy through Deep Human-in-the-Loop Reinforcement Learning
S Reddy, A Dragan, S Levine
Publication Submission Form
ZAM Marinho, AFT Martins, SB Cohen, NA Smit, A Dragan, A Byravan, ...
Scalable Confidence-Aware Safety Analysis for Robot Planning around Multiple Humans
JF Fisac, D Fridovich-Keil, A Bajcsy, S Herbert, S Deglurkar, C Tomlin, ...
Collaborators: Dorsa Sadigh, Chandrayee Basu, Sanjit Seshia
A Dragan
Report: Verifiable Control for (Semi) Autonomous Cars that Learns from Human (Re) Actions
A Dragan, SS Sastry, SA Seshia
Planning with Observable Operator Models Guided Research Final Report
A Dragan
Trajectory Optimization for Predictable and Legible Motion
AD Dragan, SS Srinivasa






* * * 

To William Hague, the new Chancellor of Oxford University ~ #OxfordWUaScollaborations ?

general@williamjhague.com - October 2025

Scott MacLeod sgkmacleod@worlduniversityandschool.org

5:21 PM (1 hour ago)
to general


Dear Chancellor Hague, 

Greetings from the SF Bay Area and free-to-students' CC-4 licensed  MIT OCW-centric wiki World University and School WUaS seeking to grow major online research universities in all ~200 countries and in all 7159 languages, and seeking to get reimbursement from all ~200 countries and all 50 US states, ministries/departments of education (due to CC-4 licensed MIT OCW), and see these 2 iterations of MIT OCW - https://ocw.mit.edu/ and and here with 7 languages - https://opencw.aprende.org/courses/translated-courses/ + https://opencw.aprende.org/courses/. Thanks for your TwitterX posts recently regarding Oxford and your new Chancellorship (in the PSs), and Congratulations. Brainstorming, how might MIT OCW-centric wiki World University and School WUaS and Oxford University collaborate well into the future, and as WUaS seeks to become the Harvard / MIT / Stanford / Oxbridge / other greatest universities in all ~200 countries, of the Internet ... and in their main and all languages, and even to hire and employ 2.5 million people, such as Oxonian graduates, - over the next 50-100 years, and on both of our WUaS wings, 1) the non-profit 501 c 3, and 2) the parallel for profit general stock company legal entity in the state of California, an academic press planned in all 7159 living languages, and with Physical-Digital WUaS Educational Services' Stores (and think Walmart in 19 out of 200 countries) .. about which you can see further here, and even regarding Artificial Intelligence in the BoardRoom, having just attended a Stanford Law Rock Center webinar on this, where I asked - 

"How do you think ChatGPT would inform Boards at 501 c 3 universities, such as at Yale or Harvard, compared with Boards at for-profit general stock companies? (I ask in developing Boards for MIT OCW-centric wiki World Univ & Sch which has both legal entities 501 c 3 Nonprofit http://worlduniversityandschool.org/ - and the For-Profit general stock company legal entity in the state of CA, WUaS Corp  http://worlduniversityandschool.org/AcademicPress.html)" (and see the tax numbers at the bottom to get an idea of how these wings will work with extraordinary synergies between these wings). 

Thanks so much, and congratulations, and all the best, 

Scott GK MacLeod




Eagle (Aquila): World University and Schools' worldwide abolition movement to protect people from modern slavery is growing

Lake Clark Wilderness, AK: Recording of the M 10/6/25 open WUaS Weekly Business Meeting (conducted loosely in the manner of Friends / Quaker, and open), and please see these blog posts (in daily blog @ https://scott-macleod.blogspot.com) * And for next week's 10/13/25 WUaS Weekly Business Meeting Agenda and News, please see - https://worlduniversityandschool.blogspot.com/2025/10/lake-clark-wilderness-ak-m-10625-m.html ... * * (was - M 10/6/25 & M 10/13/25 open MIT OCW-centric wiki World Univ & Sch WUaS News and Q&A, with Zoom URL





PS

William Hague
@WilliamJHague
·
Nov 27, 2024
It is the greatest honour of my life to have been chosen by my fellow Oxonians to serve as Chancellor of our university.

https://x.com/WilliamJHague/status/1861780279334928710


PPS 
William Hague
@WilliamJHague
·
Oct 9
Ten years at number one.

@UniofOxford
 has again been ranked the world’s leading university in the
@timeshighered
 World University Rankings - a decade of global excellence in research, teaching and innovation.

https://x.com/WilliamJHague/status/1976256966734270494





PPPS
My notes - 





William Hague's Oxford Studies

William Hague studied Philosophy, Politics and Economics (PPE) at Magdalen College, Oxford.





--

Society, Information Technology, and the Global University (2025, forthcoming) 



- Scott GK MacLeod  
Founder, President, CEO, Professor & Presiding Clerk (loosely in the manner of unprogrammed Friends / Quakers)
CC-4 licensed MIT OCW-centric, Wiki, 
World University & School (WUaS) 
- USPS US Post Office, General Delivery, Canyon, CA 94516 


1) non-profit 501(c)(3) Public Charity 
MIT OCW-centric, 
World University and School - http://worlduniversityandschool.org 

2) for profit general stock company WUaS Corporation in CA - http://worlduniversityandschool.org/AcademicPress.html

(m) 412 478 0116 - sgkmacleod@gmail.com 







* 




























https://en.wikipedia.org/wiki/Western_capercaillie

https://commons.wikimedia.org/wiki/Category:Tetrao_urogallus

...



Posted by at
Labels: , , , , , , , , , , , , , , , , ,

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)