Program

Tentative schedule

Monday 26th

9:00 am - 10:30 am

    • Welcome and Introductions
    • Piotr Gmytrasiewicz, George Moe and Adolfo Moreno. Interactive Agent that Understands the User.
    • Magnus Boman, Magnus Sahlgren, Olof Görnerup and Daniel Gillblad. Learning Machines.

10:30 am - 11:00 am: Break

11:00 am - 12:30 pm

    • Invited Speaker: Pradeep Varakantham
    • Shayegan Omidshafiei, Jason Pazis, Christopher Amato and Jonathan How. Decentralized Multitask Multiagent Reinforcement Learning.

12:30 pm - 2:00 pm: Lunch

2:00 pm - 3:30 pm

    • Invited Speaker, Mykel Kochenderfer: Multiagent Control for Safety Critical Applications
    • Richard Klima, Karl Tuyls and Frans Oliehoek. Model-based Reinforcement Learning under Periodical Observability.

3:30 pm - 4:00 pm: Break

4:00 pm - 5:30 pm

Discussion and networking

6:00 pm - 7:00 pm: Reception

Tuesday 27th

9:00 am - 10:30 am

    • Invited Speaker: Ann Nowe
    • Panayiotis Danassis and Boi Faltings. Learning in Ad-hoc Anti-coordination Scenarios.

10:30 am - 11:00 am: Break

11:00 am - 12:30 pm

    • Yanlin Han and Piotr Gmytrasiewicz. Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs.
    • Richard Everett and Stephen Roberts. Opponent Modelling of Non-Stationary Agents with Deep Reinforcement Learning.
    • Sam Ganzfried and Qinyung Sun. Bayesian Opponent Exploitation in Imperfect-Information Games.

12:30 pm - 2:00 pm: Lunch

2:00 pm - 3:30 pm

    • Invited Speaker: Mac Schwager
    • Bill Squires. Toward LfD Training of Heterogeneous Swarm Behaviors.

3:30 pm - 4:00 pm: Break

4:00 pm - 5:30 pm

break out sessions

6:00 pm - 7:00 pm: Plenary Session

Wednesday 28th

9:00 am - 10:30 am

    • Invited Speaker, Igor Mordatch: Emergence of Grounded Compositional Language in Multi-Agent Populations
    • Alexander Peysakhovich and Adam Lerer. Towards AI that can solve social dilemmas.

10:30 am - 11:00 am: Break

11:00 am - 12:30 pm

    • Invited Speaker: Emma Brunskill (joint session with SS6: Integrated Representation, Reasoning, and Learning in Robotics)
    • Concluding Discussion