Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
On the map: Offline RL and imitation learning from data → Inverse reinforcement learning
Abstract (arXiv)
Multi-agent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multi-agent system, and reconstruct utility functions of the individual agents. Motivated by the problem of detecting UAV coordination, how can we construct a statistical detector for Pareto-efficient behavior given noisy measurements of the decisions of a multi-agent system? This paper approaches this IRL problem by deriving necessary and sufficient conditions for a dataset of multi-agent system dynamics to be consistent with Pareto-efficient coordination, and providing algorithms for recovering utility functions which are consistent with the system dynamics. We derive an optimal statistical detector for determining Pareto-efficient coordination from noisy system measurements, which minimizes Type-I statistical detection error. Then, we provide a utility estimation algorithm which minimizes the worst-case estimation error over a statistical ambiguity set centered at empirical observations; this min-max solution achieves distributionally robust IRL, which is crucial in adversarial strategic interactions. We illustrate these results in a detailed example for detecting Pareto-efficient coordination among multiple UAVs given noisy measurement recorded at a radar. We then reconstruct the utility functions of the UAVs in a distributionally robust sense.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 12 of its 58 references that are in the map. First posted on arXiv 10 Sep 2025.
Builds on
12 of 58 references.
Closest ancestors · 3
Same direction, newest first
- 2022Identifying Coordination in a Cognitive Radar Network -- A Multi-Objective Inverse Reinforcement Learning Approach13 Nov
- 2022Meta-Cognition. An Inverse-Inverse Reinforcement Learning Approach for Cognitive Radars3 May
- 2019Identifying Cognitive Radars -- Inverse Reinforcement Learning using Revealed Preferences1 Dec
Other references · 9
- 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 176
- 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 170
- 2019Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Surveycited by 47
- 2020Wasserstein Distributionally Robust Look-Ahead Economic Dispatchcited by 5
- 2017Decomposition Algorithm for Distributionally Robust Optimization using Wasserstein Metriccited by 4
- 2020Wasserstein Distributionally Robust Inverse Multiobjective Optimizationcited by 4
- 2021Energy and Age Pareto Optimal Trajectories in UAV-assisted Wireless Data Collectioncited by 2
- 2023Statistical Detection of Coordination in a Cognitive Radar Network through Inverse Multi-objective Optimizationcited by 2
- 2019UAV-Enabled Covert Wireless Data Collectioncited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Distributionally Robust Inverse Reinforcement Learning for Identifying Multi-Agent Coordinated Sensing
- 2019Multi-Agent Adversarial Inverse Reinforcement Learning
- 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
- 2026Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning
- 2025Symmetry-Guided Multi-Agent Inverse Reinforcement Learning
- 2020Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic
- 2025Learning Pareto-Optimal Rewards from Noisy Preferences: A Framework for Multi-Objective Inverse Reinforcement Learning
- 2024On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning