# Learning Partial Action Replacement in Offline MARL

arXiv: https://arxiv.org/abs/2603.28573 · HTML: https://mlsanity.com/paper/2603.28573/

## Key facts

- No citing papers in the map yet (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 19 of its 22 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## 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, 19 of 19)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [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)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Offline Reinforcement Learning with Fisher Divergence Critic Regularization](https://mlsanity.com/paper/2103.08050/) (2021)
- [FACMAC: Factored Multi-Agent Centralised Policy Gradients](https://mlsanity.com/paper/2003.06709/) (2020)
- [Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.03400/) (2021)
- [Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification](https://mlsanity.com/paper/2111.11188/) (2021)
- [Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2309.12696/) (2023)
- [Partial Action Replacement: Tackling Distribution Shift in Offline MARL](https://mlsanity.com/paper/2511.07629/) (2025)

## Abstract (arXiv)

Offline multi-agent reinforcement learning (MARL) faces a critical challenge: the joint action space grows exponentially with the number of agents, making dataset coverage exponentially sparse and out-of-distribution (OOD) joint actions unavoidable. Partial Action Replacement (PAR) mitigates this by anchoring a subset of agents to dataset actions, but existing approach relies on enumerating multiple subset configurations at high computational cost and cannot adapt to varying states. We introduce PLCQL, a framework that formulates PAR subset selection as a contextual bandit problem and learns a state-dependent PAR policy using Proximal Policy Optimisation with an uncertainty-weighted reward. This adaptive policy dynamically determines how many agents to replace at each update step, balancing policy improvement against conservative value estimation. We prove a value-error bound showing that the estimation error scales linearly with the expected number of deviating agents. Compared with the previous PAR-based method SPaCQL, PLCQL reduces the number of per-iteration Q-function evaluations from n to 1, significantly improving computational efficiency. Empirically, PLCQL achieves the highest normalised scores on 66% of tasks across MPE, MaMuJoCo, and SMAC benchmarks, outperforming SPaCQL on 84% of tasks while substantially reducing computational cost.