Multi-Agent Generative Adversarial Imitation Learning

2018/07/26 by Jiaming Song, Hongyu Ren, Song, Jiaming +5 · 12 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1807.09936

openalex publication_date 2018/07/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-agent imitation learning for general Markov games, where we build upon a generalized notion of inverse reinforcement learning. We further introduce a practical multi-agent actor-critic algorithm with good empirical performance. Our method can be used to imitate complex behaviors in high-dimensional environments with multiple cooperative or competing agents.

Cited by

• A first-order method for nonconvex-strongly-concave constrained minimax optimization
• Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation
• R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
• Rate optimal learning of equilibria from data
• DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
• MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
• Symmetry-Guided Multi-Agent Inverse Reinforcement Learning
• Inference of Altruism and Intrinsic Rewards in Multi-Agent Systems
• LLM-Enhanced Multi-Agent Reinforcement Learning with Expert Workflow for Real-Time P2P Energy Trading
• GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
• Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning
• Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts

Related

• Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games
• Generative Adversarial Imitation Learning
• Structured Imitation Learning of Interactive Policies through Inverse Games
• Multi-Agent Adversarial Inverse Reinforcement Learning
• Generating Personas for Games with Multimodal Adversarial Imitation Learning