On Feasible Rewards In Multi-agent Inverse Reinforcement Learning

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfreihaut2024on

Related papers

• Multi-agent Inverse Reinforcement Learning: Suboptimal Demonstrations And Alternative Solution Concepts (2021)0.00
• Adversarial Inverse Reinforcement Learning For Mean Field Games (2021)0.00
• Multi-agent Inverse Reinforcement Learning For Certain General-sum Stochastic Games (2018)10.97
• Incentivize Without Bonus: Provably Efficient Model-based Online Multi-agent RL For Markov Games (2025)0.00
• Scalable Multi-agent Inverse Reinforcement Learning Via Actor-attention-critic (2020)0.00
• MIR: Efficient Exploration In Episodic Multi-agent Reinforcement Learning Via Mutual Intrinsic Reward (2025)0.00
• Achieving Fairness In Multi-agent Markov Decision Processes Using Reinforcement Learning (2023)0.00
• Discovering Individual Rewards In Collective Behavior Through Inverse Multi-agent Reinforcement Learning (2023)0.00