Woojun Kim

Learning Communication in Offline Multi-Agent Reinforcement Learning

MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals

Efficient Zero-Shot Coordination via Offline Policy Diversity and Online Belief Reasoning

Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment

Adaptively Coordinating with Novel Partners via Learned Latent Strategies