Multi-agent Interactions Modeling With Correlated Policies

Abstract

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at https://github.com/apexrl/CoDAIL.

Stats

• citations0
• S2 citations—
• github stars19
• HF likes0
• heat score2.60
• arxiv keyliu2020multi

Code

• apexrl/CoDAIL—

Related papers

• Imitation Learning Of Correlated Policies In Stackelberg Games (2025)0.00
• Cooperative Multi-agent Policy Gradients With Sub-optimal Demonstration (2018)0.00
• Multi-agent Cooperation Through Learning-aware Policy Gradients (2024)0.00
• Context-aware Bayesian Network Actor-critic Methods For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Agentmixer: Multi-agent Correlated Policy Factorization (2024)0.00
• Metric Policy Representations For Opponent Modeling (2021)0.00
• Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games (2023)0.00