Minghuan Liu

reinforcement learning (4) dynamics model (2) proximal policy optimization (2) sample efficiency (2) offline reinforcement learning (2) multi-agent system (2) trajectory prediction (1) prompt-based learning (1) policy optimization (1) attention mechanism (1) curriculum learning (1) depth estimation (1) feature learning (1) policy learning (1) humanoid robot (1) policy gradient (1) behavior cloning (1) importance sampling (1) multi-agent learning (1) imperfect information (1)