Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
The discovery of individual objectives in collective behavior of complex dynamical systems such as fish schools and bacteria colonies is a long-standing challenge. Inverse reinforcement learning is a potent approach for addressing this challenge but its applicability to dynamical systems, involving continuous state-action spaces and multiple interacting agents, has been limited. In this study, we tackle this challenge by introducing an off-policy inverse multi-agent reinforcement learning algorithm (IMARL). Our approach combines the ReF-ER techniques with guided cost learning. By leveraging demonstrations, our algorithm automatically uncovers the reward function and learns an effective policy for the agents. Through extensive experimentation, we demonstrate that the proposed policy captures the behavior observed in the provided data, and achieves promising results across problem domains including single agent models in the OpenAI gym and multi-agent models of schooling behavior. The present study shows that the proposed IMARL algorithm is a significant step towards understanding collective dynamics from the perspective of its constituents, and showcases its value as a tool for studying complex physical systems exhibiting collective behaviour.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 17 May 2023.
Builds on
18 of 43 references.
References · 18
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2016Generative Adversarial Imitation Learningcited by 1,597
- 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
- 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
- 2019Machine Learning for Fluid Mechanicscited by 385
- 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 176
- 2020Game-Theoretic Multiagent Reinforcement Learningcited by 94
- 2019Multi-Agent Adversarial Inverse Reinforcement Learningcited by 60
- 2021Scientific multi-agent reinforcement learning for wall-models of turbulent flowscited by 52
- 2018Remember and Forget for Experience Replaycited by 43
6 more
- 2021Learning Efficient Navigation in Vortical Flow Fieldscited by 26
- 2022Fusion of Probability Density Functionscited by 22
- 2016Inverse Reinforcement Learning in Swarm Systemscited by 18
- 2020Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Criticcited by 6
- 2020Korali: Efficient and Scalable Software Framework for Bayesian Uncertainty Quantification and Stochastic Optimizationcited by 4
- 2022Remember and Forget Experience Replay for Multi-Agent Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2022Individual-Level Inverse Reinforcement Learning for Mean Field Games
- 2026Unveiling Complex Collective Behaviors from Simple Rewards
- 2020Bayesian Inverse Reinforcement Learning for Collective Animal Movement
- 2025Symmetry-Guided Multi-Agent Inverse Reinforcement Learning
- 2025Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
- 2024On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- 2024The impact of behavioral diversity in multi-agent reinforcement learning
- 2021Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts