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.

The most commonly used neural network models are not well suited to direct digital implementations because each node needs to perform a large number of operations between floating point values. Fortunately, the ability to learn from examples and to generalize is not restricted to networks ofthis type. Indeed, networks where each node implements a simple Boolean function (Boolean networks) can be designed in such a way as to exhibit similar properties. Two algorithms that generate Boolean networks from examples are presented. The results show that these algorithms generalize very well in a class of problems that accept compact Boolean network descriptions. The techniques described are general and can be applied to tasks that are not known to have that characteristic. Two examples of applications are presented: image reconstruction and handwritten character recognition.

The most commonly used neural network models are not well suited to direct digital implementations because each node needs to perform a large number of operations between floating point values. Fortunately, the ability to learn from examples and to generalize is not restricted to networks ofthis type. Indeed, networks where each node implements a simple Boolean function (Boolean networks) can be designed in such a way as to exhibit similar properties. Two algorithms that generate Boolean networks from examples are presented. The results show that these algorithms generalize very well in a class of problems that accept compact Boolean network descriptions. The techniques described are general and can be applied to tasks that are not known to have that characteristic. Two examples of applications are presented: image reconstruction and handwritten character recognition.

The most commonly used neural network models are not well suited to direct digital implementations because each node needs to perform alarge number of operations between floating point values. Fortunately, the ability to learn from examples and to generalize is not restricted to networks ofthis type. Indeed, networks where each node implements a simple Boolean function (Boolean networks) can be designed in such a way as to exhibit similar properties. Two algorithms that generate Boolean networks from examples are presented. Theresults show that these algorithms generalize very well in a class of problems that accept compact Boolean network descriptions.