500AI
Back to researchers

Simon Schmitt

Planning with learned dynamics (MuZero)

Co-authored MuZero: planning with a learned model across games and Atari.

Highlights

DeepMindModel-based RLPlanning
Focus: Planning with learned dynamics (MuZero)
Why it matters: Co-authored MuZero: planning with a learned model across games and Atari.
Start here
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelpaper →

Research Areas

DeepMindModel-based RLPlanning
Simon Schmitt - AI Researcher Profile | 500AI