Adversarial Inverse Reinforcement Learning For Mean Field Games

Abstract

Mean field games (MFGs) provide a mathematically tractable framework for modelling large-scale multi-agent systems by leveraging mean field theory to simplify interactions among agents. It enables applying inverse reinforcement learning (IRL) to predict behaviours of large populations by recovering reward signals from demonstrated behaviours. However, existing IRL methods for MFGs are powerless to reason about uncertainties in demonstrated behaviours of individual agents. This paper proposes a novel framework, Mean-Field Adversarial IRL (MF-AIRL), which is capable of tackling uncertainties in demonstrations. We build MF-AIRL upon maximum entropy IRL and a new equilibrium concept. We evaluate our approach on simulated tasks with imperfect demonstrations. Experimental results demonstrate the superiority of MF-AIRL over existing methods in reward recovery.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2021adversarial

Related papers

• Kernel Based Maximum Entropy Inverse Reinforcement Learning For Mean-field Games (2025)0.00
• On Feasible Rewards In Multi-agent Inverse Reinforcement Learning (2024)0.00
• Maximum Causal Entropy IRL In Mean-field Games And GNEP Framework For Forward RL (2024)0.00
• On Imitation In Mean-field Games (2023)0.00
• Deep Reinforcement Learning For Infinite Horizon Mean Field Problems In Continuous Spaces (2023)3.58
• Population-aware Online Mirror Descent For Mean-field Games By Deep Reinforcement Learning (2024)0.00
• Reinforcement Learning For Mean Field Games With Strategic Complementarities (2020)0.00
• Multi-agent Inverse Reinforcement Learning: Suboptimal Demonstrations And Alternative Solution Concepts (2021)0.00