Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first.

Added to korrents 12 Sept 2025 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Once a robot is good enough, you can teach it with words instead of with demonstrations, and language becomes a training signal for motor skill. SLSergey Levine12 Sept 2025similar wording
• Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. CFChelsea Finn12 Aug 2026similar wording
• One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for. CFChelsea Finn12 Aug 2026similar wording
• Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. AKAndrej Karpathy17 Oct 2025similar wording
• Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world. RSRichard Sutton26 Sept 2025similar wording

See this on the map →