Reinforcement Learning with Large Datasets: Robotics, Image Generation, and LLMs

[@icriou]

Simply beautiful. Research from this lab is the bliss of open source AI since leading industrial labs may go dark forest after gpt4 level LLM.

[@parvezalam5153]

Interesting talk.

[@matthewpublikum3114]

Alphago learns through self play, which means move 37 is in distribution but out of distribution with respect to human play.