Program
(All Times are Vienna time)
Opening Remarks 9:00 - 9:10
9:10
Ice Breaker - Hanabi game
9:40
Discussion - Benchmarks for Ad-hoc teamwork
10:00
Multi-Agent Reinforcement Learning towards Zero-Shot Communication
Break 11:00-11:15
11:15
João Ribeiro, Cassandro Martinho, Alberto Sardinha and Francisco S. Melo / Making Friends in the Dark: Ad Hoc Teamwork under Partial Observability
Arrasy Rahman, Elliot Fosong, Ignacio Carlucho and Stefano V. Albrecht / Towards Robust Ad Hoc Teamwork Agents By Creating Diverse Training Teammates
Ram Rachum / Fruit Slots: Experimenting with an Autocurriculum of Implicit Communication in Reinforcement Learning Agents
Elliot Fosong, Muhammad Arrasy Rahman, Ignacio Carlucho and Stefano V. Albrecht / Few Shot Teamwork
Lunch break 12:15-13:15
13:15
Dan Kröhling, Omar Chiotti and Ernesto Martínez / Artificial Theory of Mind in Contextual Automated Negotiations
Matthias Gerstgrasser and Sarah Keren / Collaboration Promotes Team Resilience in Multi-Agent Reinforcement
Yair Hanina, Reuth Mirsky, William Macke and Peter Stone / Quantifying Human Rationality in Ad-hoc Teamwork
Kyle Tilbury and Jesse Hoey / Identity and Dynamic Teams in Social Dilemmas
Ignacio Carlucho, Muhammad Arrasy Rahman, William Ard, Elliot Fosong, Corina Barbalata and Stefano Albrecht / Cooperative Marine Operations via Ad Hoc Teams
14:30
Poster session + Highlights on recently accepted papers
Anirudh Kakarlapudi, Gayathri Anil, Adam Eck, Prashant Doshi, Leen-Kiat Soh / Decision-Theoretic Planning with Communication in Open Multiagent Systems (Accepted to UAI 2022)
Varun Babbar, Umang Bhatt, Adrian Weller / On the Utility of Prediction Sets in Human-AI Teams (Accepted to IJCAI 2022)
Leo Amado, Reuth Mirsky, Felipe Meneguzzi / Goal Recognition as Reinforcement Learning (Accepted to AAAI 2022)
Thomy Phan, Felix Sommer, Philipp Altmann, Fabian Ritz, Lenz Belzner and Claudia Linnhoff-Popien / Emergent Cooperation from Mutual Acknowledgment Exchange (Accepted to AAMAS 2022)
Hao Chen, Guangkai Yang, Junge Zhang, Qiyue Yin, and Kaiqi Huang / RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning (Accepted to IJCNN 2022)
Break 15:00-15:15
15:15
RoboCup Drop in Player Challenges: A Testbed for Ad Hoc Teamwork
16:15
Explainability: The Not-So-Secret Weapon for Ad Hoc Coordination
17:15
Conclusion and wrap up