# Multi-Agent Interactions Modeling with Correlated Policies

arXiv: https://arxiv.org/abs/2001.03415 · HTML: https://mlsanity.com/paper/2001.03415/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 4 Jan 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 13 of 13)

- [Robust Imitation Learning against Variations in Environment Dynamics](https://mlsanity.com/paper/2206.09314/) (2022)
- [PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration](https://mlsanity.com/paper/2203.08553/) (2022)
- [Multi-Agent Imitation Learning with Copulas](https://mlsanity.com/paper/2107.04750/) (2021)
- [Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2312.09539/) (2023)
- [Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.06042/) (2021)
- [CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces](https://mlsanity.com/paper/2211.15824/) (2022)
- [A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.00451/) (2023)
- [Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations](https://mlsanity.com/paper/2205.02959/) (2022)
- [Decision-making with Speculative Opponent Models](https://mlsanity.com/paper/2211.11940/) (2022)
- [Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations](https://mlsanity.com/paper/2502.17618/) (2025)
- [Imitation Learning of Correlated Policies in Stackelberg Games](https://mlsanity.com/paper/2503.08883/) (2025)
- [TacSIm: A Dataset and Benchmark for Football Tactical Style Imitation](https://mlsanity.com/paper/2603.25199/) (2026)
- [Implicit Neural Representations of Individual Behavior](https://mlsanity.com/paper/2606.12200/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/apexrl/CoDAIL.