Cooperative AI Workshop
NeurIPS 2020

Program Details

The workshop will feature invited talks by researchers from diverse disciplines and backgrounds, ranging from AI and machine learning to political science, economics, and law.

We will have a virtual poster session for presenting work submitted to the workshop. Poster sessions will be hosted in GatherTown for participants to join the conversation and chat to the authors. We have allotted a slot for Spotlight talks, which will be mostly dedicated to junior researchers.

We intend to have a panel discussion regarding the main open questions in Cooperative AI, stimulating future research in this space.

We hope that bringing together speakers from diverse fields and views will result in useful discussions and interactions, leading to novel ideas.

Workshop Schedule

Saturday 12 December

(Note: all sessions will be pre-recorded and available to view in advance, except for the Q&A, Poster Sessions and Closing Remarks, which will take place live).

For the live Q&A sessions, participants should submit questions via the - links are available the schedule below and on the NeurIPs workshop page.

(Eastern Standard Time)

Start Time Event Speakers

  • 8:20am Welcome Yoram Bachrach (DeepMind), Gillian Hadfield (University of Toronto)

  • 8:30am Opening Remarks Allan Dafoe (University of Oxford); Thore Graepel (DeepMind)

  • 9:00am Keynote Talk Peter Stone (The University of Texas at Austin)
    Talk title: Ad Hoc Autonomous Agent Teams: Collaboration without Pre-coordination

  • 9:30am Keynote Talk Gillian Hadfield (University of Toronto)
    Talk title: The Normative Infrastructure of Cooperation

  • 10:00am Keynote Talk James Fearon (Stanford University)
    Talk title: Two Kinds of Cooperative AI Challenges: Game Play and Game Design

  • 10:30am Keynote Talk Sarit Kraus (Bar-Ilan University)
    Talk title: Agent-Human Collaboration and Learning for Improving Human Satisfaction

  • 11:00am Keynote Talk William Isaac (DeepMind)
    Talk title: Can Cooperation make AI (and Society) Fairer?

  • 11:30am (Live) General Q&A: Thore Graepel (DeepMind), Yoram Bachrach (DeepMind), Allan Dafoe (University of Oxford),
    Open Problems in AI Natasha Jaques (Google)
    -Participants to submit questions via (link here)

  • 11:45am (Live) Keynote Speaker Q&A Gillian Hadfield (University of Toronto)
    -Participants to submit questions via (link here)

  • 12:00pm (Live) Keynote Speaker Q&A William Isaac (DeepMind)
    -Participants to submit questions via (link here)

  • 12:15pm (Live) Keynote Speaker Q&A Peter Stone (The University of Texas at Austin)
    -Participants to submit questions via (link here)

  • 12:30pm (Live) Keynote Speaker Q&A Sarit Kraus (Bar-Ilan University)
    -Participants to submit questions via (link here)

  • 12:45pm (Live) Keynote Speaker Q&A James Fearon (Stanford University)
    -Participants to submit questions via (link here)

  • 1:00pm (Live) Poster Sessions Hosted in GatherTown (link available on workshop page)

  • 2:00pm Panel Discussion Kate Larson (DeepMind), Natasha Jaques (Google), Jeffrey S. Rosenschein (The Hebrew
    University of Jerusalem), Michael Wooldridge (University of Oxford)

  • 2:45pm Spotlight Talk Too many cooks: Bayesian inference for coordinating multi-agent collaboration
    Authors: Rose Wang, Sarah Wu, James Evans, Joshua Tenenbaum, David Parkes and Max Kleiman-Weiner

  • 3:00pm Spotlight Talk Learning Social Learning
    Authors: Kamal Ndousse, Douglas Eck, Sergey Levine and Natasha Jaques

  • 3:15pm Spotlight Talk Benefits of Assistance over Reward Learning
    Authors: Rohin Shah, Pedro Freire, Neel Alex, Rachel Freedman, Dmitrii Krasheninnikov, Lawrence Chan,
    Michael Dennis, Pieter Abbeel, Anca Dragan and Stuart Russell

  • 3:30pm Spotlight Talk Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
    Authors: Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Josh Tenenbaum, Sanja Fidler and Antonio Torralba

  • 3:45pm (Live) Closing Remarks Eric Horvitz (Microsoft)