OpenAI 联合创始人 · Co-founder, OpenAI
OpenAI 联合创始人，PPO 算法及 ChatGPT 背后大量 RLHF 技术的发明者，后加入 Anthropic。语言模型强化学习的核心人物。
Co-founder of OpenAI and inventor of PPO and much of the RLHF stack behind ChatGPT; later joined Anthropic. A central figure in RL for language models.
在 AI Paper 查看 TA 的全部论文 →