Dongbin Zhao

offline reinforcement learning (3) decision transformer (2) world model (2) multi-agent reinforcement learning (1) zero-shot learning (1) sample efficiency (1) reinforcement learning (1) task generalization (1) policy optimization (1) robotic manipulation (1) self-supervised learning (1) chain-of-thought reasoning (1) autonomous driving (1) trajectory prediction (1) visual reinforcement learning (1) trajectory modeling (1) reward modeling (1) out-of-distribution generalization (1) behavior cloning (1) sequence modeling (1)