# MARPO: A Reflective Policy Optimization for Multi Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.22832 · HTML: https://mlsanity.com/paper/2512.22832/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2025.

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

- [Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2605.11880/) (2026)

## Abstract (arXiv)

We propose Multi Agent Reflective Policy Optimization (MARPO) to alleviate the issue of sample inefficiency in multi agent reinforcement learning. MARPO consists of two key components: a reflection mechanism that leverages subsequent trajectories to enhance sample efficiency, and an asymmetric clipping mechanism that is derived from the KL divergence and dynamically adjusts the clipping range to improve training stability. We evaluate MARPO in classic multi agent environments, where it consistently outperforms other methods.