Hangyu Mao

multi-agent reinforcement learning (5) deep reinforcement learning (3) reinforcement learning (2) knowledge distillation (2) centralized training decentralized execution (2) cooperative game (2) multi-agent system (2) value function approximation (1) value function (1) in-context learning (1) mutual information (1) continuous control (1) cooperative multi-agent (1) resource allocation (1) policy learning (1) value factorization (1) proximal policy optimization (1) question answering (1) tool use (1) decision tree (1)