# Partial Action Replacement: Tackling Distribution Shift in Offline MARL

arXiv: https://arxiv.org/abs/2511.07629 · HTML: https://mlsanity.com/paper/2511.07629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Offline multi-agent RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Offline RL and imitation learning from data / [Offline multi-agent RL](https://mlsanity.com/offlinerl/offline-multi-agent-rl/)

## Builds on (most cited first, 14 of 14)

- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1905.05408/) (2019)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [Multiagent Cooperation and Competition with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.08779/) (2015)
- [Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification](https://mlsanity.com/paper/2111.11188/) (2021)
- [Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization](https://mlsanity.com/paper/2307.11620/) (2023)
- [A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem](https://mlsanity.com/paper/2305.17198/) (2023)
- [Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization](https://mlsanity.com/paper/2306.08900/) (2023)

## Built on by (most cited first, 1 of 1)

- [Learning Partial Action Replacement in Offline MARL](https://mlsanity.com/paper/2603.28573/) (2026)

## Abstract (arXiv)

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.