Haosheng Zou

reinforcement learning (2) multi-task learning (1) curriculum learning (1) mathematical reasoning (1) model distillation (1) chain-of-thought reasoning (1) policy learning (1) hierarchical reinforcement learning (1) model training (1) language model (1) task distribution (1) supervised fine-tuning (1) reward shaping (1) intrinsic reward (1) credit assignment (1) process supervision (1) long context (1) first-person shooter (1) option framework (1) chain of thought (1)