R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Harsh Goel; Mohammad Omama; Behdad Chalaki; Vaishnav Tadiparthi; Ehsan Moradi Pari; Sandeep P. Chinchali

2025 ICML ICML 2025

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Harsh Goel, Mohammad Omama, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi Pari, Sandeep P. Chinchali

Topics

Reinforcement Learning > Methods > Multi-Agent Systems Reinforcement Learning > Methods > Model-Based RL

Keywords

contrastive learning mutual information intrinsic reward dynamics model role discovery diversity

Download PDF