Shihong Deng

chain of thought (2) sample efficiency (1) offline reinforcement learning (1) policy gradient (1) error propagation (1) sparse reward (1) experience replay (1) negative sample (1) potential energy (1) hard exploration (1) intrinsic state supervision (1) self-imitation learning (1) process reward model (1) negative sample augmentation (1) large language model (1) reasoning step (1) reinforcement learning (1) behavior constrained (1)