Poramate Manoonpong

reinforcement learning (1) mutual information (1) constraint satisfaction (1) generalization ability (1) cooperative agent (1) partner diversity (1) agent specialization (1) overfitting mitigation (1) real-world reinforcement learning (1) multi-agent system (1) partner specialization (1) reward gain adaptation (1) constrained locomotion learning (1) reward weighting (1) quadruped robot locomotion (1)