On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
Till Freihaut, Giorgia Ramponi
Abstract
Multi-agent inverse reinforcement learning (MAIRL) aims to recover agent reward functions from expert demonstrations. We characterize the feasible reward set in Markov games, identifying all reward functions that rationalize a given equilibrium. However, equilibrium-based observations are often ambiguous: a single Nash equilibrium can correspond to many reward structures, potentially changing the game's nature in multi-agent systems. We address this by introducing entropy-regularized Markov games, which yield a unique equilibrium while preserving strategic incentives. For this setting, we provide a sample complexity analysis detailing how errors affect learned policy performance. Our work establishes theoretical foundations and practical insights for MAIRL.
BibTeX
@inproceedings{
freihaut2025on,
title={On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning},
author={Till Freihaut and Giorgia Ramponi},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=qu6mRbSnUs}
}