What Sergey Levine thinks about reinforcement learning

@sergey-levine · 24 positions · On ppll ↗

Professor of computer science at UC Berkeley, and a co-founder of the robotic foundation model company Physical Intelligence.

Sergey Levine did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter reinforcement learning · Newest first

Topic

All 24 robotics 18 LLMs 3 computer vision 2 reinforcement learning 2 self-driving cars 2 world models 2 chat interfaces 1 scaling laws 1 semiconductors 1

Sort

Newest Oldest

Only Sergey Levine on reinforcement learning. See everyone on reinforcement learning

2 dated positions, 2025, in their own words. Our reading of what Sergey Levine has said — not written or endorsed by them.

2 positions so far — this page is not yet offered to search engines.

12 Sept 2025

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

robotics

Their wordsUh so in order to effectively learn from your own experience, it turns out that it's really really important to already know something about what you're doing. Otherwise, it takes far too long.

↗Fully autonomous robots are much closer than you think – Sergey Levineyoutube.com 17th of 24 in this recording
12 Sept 2025

Our readingThe goal was never good simulation; it was answering counterfactuals, and a value function does that job as well as a simulator does.

Their wordsIt tells us that the key is not necessarily to do really good simulation. The key is to figure out how to answer counterfactuals.

↗Fully autonomous robots are much closer than you think – Sergey Levineyoutube.com 21st of 24 in this recording