微软副总裁X上「开课」，连更关于RL的一切，LLM从业者必读
"PPO" 相关文章
The State of Reinforcement Learning for LLM Reasoning
更长思维并不等于更强推理性能，强化学习可以很简洁
从PPO到GRPO，DeepSeek-R1做对了什么？
【NLP】万字长文梳理LLM+RL(HF)的脉络
Allen Institute for AI Releases Tulu 2.5 Suite on Hugging Face: Advanced AI Models Trained with DPO and PPO, Featuring Reward and Value Models
