Muning Wen

reinforcement learning (3) multi-agent reinforcement learning (3) few-shot learning (1) offline reinforcement learning (1) policy optimization (1) sim-to-real transfer (1) policy gradient (1) llm evaluation (1) humanoid robot (1) parallel computing (1) exploration exploitation (1) variance reduction (1) optimal baseline (1) language model (1) gradient estimator (1) proximal policy optimization (1) on-policy learning (1) sequence model (1) credit assignment (1) multi-turn dialogue (1)