# Multiagent Inverse Reinforcement Learning via Theory of Mind Reasoning

arXiv: https://arxiv.org/abs/2302.10238 · HTML: https://mlsanity.com/paper/2302.10238/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 8 of 8)

- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [Multi-Agent Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1907.13220/) (2019)
- [Multi-agent Inverse Reinforcement Learning for Two-person Zero-sum Games](https://mlsanity.com/paper/1403.6508/) (2014)
- [Scalable Planning and Learning for Multiagent POMDPs: Extended Version](https://mlsanity.com/paper/1404.1140/) (2014)
- [Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations](https://mlsanity.com/paper/1801.02124/) (2018)

## Built on by (most cited first, 11 of 11)

- [Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2307.01158/) (2023)
- [Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds](https://mlsanity.com/paper/2405.16439/) (2024)
- [iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.06236/) (2023)
- [Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning](https://mlsanity.com/paper/2507.03682/) (2025)
- [Spontaneous Theory of Mind for Artificial Intelligence](https://mlsanity.com/paper/2402.13272/) (2024)
- [MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind](https://mlsanity.com/paper/2603.00808/) (2026)
- [EMOTE: An Explainable architecture for Modelling the Other Through Empathy](https://mlsanity.com/paper/2306.00295/) (2023)
- [Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms](https://mlsanity.com/paper/2410.21882/) (2024)
- [ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policies](https://mlsanity.com/paper/2502.18438/) (2025)
- [DIML: Differentiable Inverse Mechanism Learning from Behaviors of Multi-Agent Learning Trajectories](https://mlsanity.com/paper/2601.17678/) (2026)
- [Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces](https://mlsanity.com/paper/2608.11354/) (2026)

## Abstract (arXiv)

We approach the problem of understanding how people interact with each other in collaborative settings, especially when individuals know little about their teammates, via Multiagent Inverse Reinforcement Learning (MIRL), where the goal is to infer the reward functions guiding the behavior of each individual given trajectories of a team's behavior during some task. Unlike current MIRL approaches, we do not assume that team members know each other's goals a priori; rather, that they collaborate by adapting to the goals of others perceived by observing their behavior, all while jointly performing a task. To address this problem, we propose a novel approach to MIRL via Theory of Mind (MIRL-ToM). For each agent, we first use ToM reasoning to estimate a posterior distribution over baseline reward profiles given their demonstrated behavior. We then perform MIRL via decentralized equilibrium by employing single-agent Maximum Entropy IRL to infer a reward function for each agent, where we simulate the behavior of other teammates according to the time-varying distribution over profiles. We evaluate our approach in a simulated 2-player search-and-rescue operation where the goal of the agents, playing different roles, is to search for and evacuate victims in the environment. Our results show that the choice of baseline profiles is paramount to the recovery of the ground-truth rewards, and that MIRL-ToM is able to recover the rewards used by agents interacting both with known and unknown teammates.