# Symmetry-Guided Multi-Agent Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.08257 · HTML: https://mlsanity.com/paper/2509.08257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 15 of 15)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [Why is Posterior Sampling Better than Optimism for Reinforcement Learning?](https://mlsanity.com/paper/1607.00215/) (2016)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Multi-Agent Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1907.13220/) (2019)
- [Multi-Agent MDP Homomorphic Networks](https://mlsanity.com/paper/2110.04495/) (2021)
- [Multi-agent Inverse Reinforcement Learning for Two-person Zero-sum Games](https://mlsanity.com/paper/1403.6508/) (2014)
- [Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach](https://mlsanity.com/paper/2105.08268/) (2021)
- [Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks](https://mlsanity.com/paper/2407.08164/) (2024)
- [Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2401.00167/) (2023)
- [ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2307.16186/) (2023)
- [Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic](https://mlsanity.com/paper/2002.10525/) (2020)
- [SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding](https://mlsanity.com/paper/2502.06440/) (2025)

## Abstract (arXiv)

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement Learning (IRL) addresses this problem by inferring implicit reward functions from expert demonstrations. Nevertheless, existing methods rely heavily on large amounts of expert demonstrations to accurately recover the reward function. The high cost of collecting expert demonstrations in robotic applications, particularly in multi-robot systems, severely hinders the practical deployment of IRL. Consequently, improving sample efficiency has emerged as a critical challenge in multi-agent inverse reinforcement learning (MIRL). Inspired by the symmetry inherent in multi-agent systems, this work theoretically demonstrates that leveraging symmetry enables the recovery of more accurate reward functions. Building upon this insight, we propose a universal framework that integrates symmetry into existing multi-agent adversarial IRL algorithms, thereby significantly enhancing sample efficiency. Experimental results from multiple challenging tasks have demonstrated the effectiveness of this framework. Further validation in physical multi-robot systems has shown the practicality of our method.