6 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…
State-Constrained Offline Reinforcement Learning
Charles A. Hepburn, Yue Jin, Giovanni Montana
Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution p…
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…
Temporal Encoding Strategies for Energy Time Series Prediction
Aayam Bansal, Keertan Balaji, Zeus Lalani
In contemporary power systems, energy consumption prediction plays a crucial role in maintaining grid stability and resource allocation enabling power companies to minimize energy…
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…