Learning from a reward ten years away is a solved problem: a value function trained by temporal-difference learning rewards the steps along the way.

Added to korrents 26 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.

• Value functions only make reinforcement learning faster: anything you can do with one you can also do without it, just more slowly. ISIlya Sutskever25 Nov 2025similar wording
• Computer-use agents had to wait for language models: without pre-trained representations the reward is too sparse to ever learn from. AKAndrej Karpathy17 Oct 2025similar wording
• The goal was never good simulation; it was answering counterfactuals, and a value function does that job as well as a simulator does. SLSergey Levine12 Sept 2025similar wording
• To reward the instinct that a new idea is worth having, training would have to score the smallness of the concepts a solution needs, not just whether it solved the problem. GSGrant Sanderson30 Jun 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

On the map

Open the map on its own page →