Weixun Wang

multi-agent reinforcement learning (7) large language model (5) reinforcement learning (5) deep reinforcement learning (3) policy transfer (3) transfer learning (2) reward modeling (2) critic model (2) graph neural network (2) policy learning (2) model alignment (2) reward shaping (2) option learning (2) chain-of-thought reasoning (1) question answering (1) knowledge distillation (1) attention mechanism (1) policy optimization (1) direct preference optimization (1) instruction following (1)