Yuhui Wang

reinforcement learning (4) large language model (3) deep reinforcement learning (2) trust region (2) language model (2) sample efficiency (2) proximal policy optimization (2) variational inference (1) mathematical reasoning (1) policy optimization (1) sequential decision making (1) question answering (1) chain-of-thought reasoning (1) video understanding (1) robot control (1) uncertainty quantification (1) partially observable markov decision process (1) behavior cloning (1) belief propagation (1) instruction tuning (1)