Muesli: Combining Improvements in Policy Optimization
Matteo Hessel ⋅ Ivo Danihelka ⋅ Fabio Viola ⋅ Arthur Guez ⋅ Simon Schmitt ⋅ Laurent Sifre ⋅ Theophane Weber ⋅ David Silver ⋅ Hado van Hasselt
2021 Spotlight
Abstract
We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero's state-of-the-art performance on Atari. Notably, Muesli does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines. The Atari results are complemented by extensive ablations, and by additional results on continuous control and 9x9 Go.
Video
Chat is not available.
Successful Page Load