Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Partial Action Replacement: Tackling Distribution Shift in Offline MARL

About

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 behavior policy is factorized - a common scenario where agents act fully or partially independently during data collection - a strategy of partial action replacement (PAR) can significantly mitigate this challenge. PAR updates a single or part of agents' actions while the others remain fixed to the behavioral data, reducing distribution shift compared to full joint-action updates. Based on this insight, we develop Soft-Partial Conservative Q-Learning (SPaCQL), using PAR to mitigate OOD issue and dynamically weighting different PAR strategies based on the uncertainty of value estimation. We provide a rigorous theoretical foundation for this approach, proving that under factorized behavior policies, the induced distribution shift scales linearly with the number of deviating agents rather than exponentially with the joint-action space. This yields a provably tighter value error bound for this important class of offline MARL problems. Our theoretical results also indicate that SPaCQL adaptively addresses distribution shift using uncertainty-informed weights. Our empirical results demonstrate SPaCQL enables more effective policy learning, and manifest its remarkable superiority over baseline algorithms when the offline dataset exhibits the independence structure.

Yue Jin, Giovanni Montana• 2025

Related benchmarks

TaskDatasetResultRank
StarCraft II micromanagementStarCraft II 2s3z medium
Win Rate46
18
StarCraft II micromanagementStarCraft II 2s3z medium_replay
Win Rate56
18
StarCraft II micromanagementStarCraft II 2s3z mixed
Win Rate96
18
StarCraft II micromanagementStarCraft II 5m_vs_6m medium
Win Rate33
18
StarCraft II micromanagementStarCraft II 5m_vs_6m medium_replay
Win Rate23
18
StarCraft II micromanagementStarCraft II 6h_vs_8z (mixed)
Win Rate52
18
StarCraft II micromanagementStarCraft II 3s_vs_5z mixed
Win Rate43
18
StarCraft II micromanagementStarCraft II 5m_vs_6m mixed
Win Rate78
18
StarCraft II micromanagementStarCraft II 6h_vs_8z medium
Test Winning Rate42
18
StarCraft II micromanagementStarCraft II 2s3z expert
Win Rate99
18
Showing 10 of 32 rows

Other info

Follow for update