Markus Wulfmeier
@m_wulfmeier
Large-Scale Interactive Intelligence - Research @GoogleDeepMind European @ELLISforEurope - priors: @oxfordrobots @berkeley_ai @ETH @MIT
ID: 4484386293
https://sites.google.com/view/mwulfmeier/bio 14-12-2015 19:55:48
2,2K Tweet
12,12K Takipçi
1,1K Takip Edilen
Imitation is the foundation of #LLM training. And it is a #ReinforcementLearning problem! Compared to supervised learning, RL -here inverse RL- better exploits sequential structure, online data and further extracts rewards. Beyond thrilled for our Google DeepMind paper! A
