Chelsea Finn 谈超越标量奖励瓶颈
I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.
AI 导读
我将发表一场演讲，探讨如何让机器人学和 LLM 超越标量奖励瓶颈。 ICML RLxF 研讨会明天下午 1:30 举行。
主题
查看原帖RL is hitting a ceiling with human feedback. What if the world itself becomes the signal? Join us at the RLxF: RL from World Feedback 🌍 workshop at ICML 2026 @icmlconf tomorrow (July 10th)! Web page: https://t.co/cN0itnL1yI https://t.co/vpMTQe4VCm
正文
当前显示原文，中文全文译文尚未就绪。
I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.
ICML RLxF workshop tomorrow at 1:30 pm.