Yann Ollivier - Universal Optimal Control, Reinforcement Learning, and Reaching Goals in LLMs
About this video
Advanced · Editorial reviewPicked one by one from a mixed channel. Transcript check: both title readers certain; 5 of 5 sampled certain picks confirmed by transcript, none failed. Channel rule:
Video by Institut des Hautes Etudes Scientifiques (IHES), played through YouTube's embedded player.
Part of Mathematics for and by Large Language Models -- 2025 Edition