“Muesli: Combining Improvements in Policy Optimization”, Matteo Hessel, Ivo Danihelka, Fabio Viola, Arthur Guez, Simon Schmitt, Laurent Sifre, Theophane Weber, David Silver, Hado van Hasselt2021-04-13 (, ; backlinks; similar)⁠:

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 9×9 Go.