5 papers
Learning Partial Action Replacement in Offline MARL
Yue Jin, Giovanni Montana
Offline multi-agent reinforcement learning (MARL) faces a critical challenge: the joint action space grows exponentially with the number of agents, making dataset coverage exponent…
Partial Action Replacement: Tackling Distribution Shift in Offline MARL
Yue Jin, Giovanni Montana
Offline multi-agent reinforcement learning (MARL) is severely hampered by the challenge of evaluating out-of-distribution (OOD) joint actions. Our core finding is that when the beh…
Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing
Yue Jin, Shuangqing Wei, Giovanni Montana
In human society, the conflict between self-interest and collective well-being often obstructs efforts to achieve shared welfare. Related concepts like the Tragedy of the Commons a…
Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning
Mianchu Wang, Yue Jin, Giovanni Montana
Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action…
Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
Ting Zhu, Yue Jin, Jeremie Houssineau +1
In decentralized multi-agent reinforcement learning, agents learning in isolation can lead to relative over-generalization (RO), where optimal joint actions are undervalued in favo…