Simon Schmitt

TL;DR: MuZero as discussed by the authors is a reinforcement learning algorithm that combines a tree-based search with a learned model to achieve state-of-the-art performance in high-performance planning and visually complex domains.

TL;DR: This work proposes to automatically adapt the contribution of each task to the agent’s updates, so that all tasks have a similar impact on the learning dynamics, and learns a single trained policy that exceeds median human performance on this multi-task domain.

TL;DR: It is shown that, on a challenging and computationally-intensive multi-task benchmark (DMLab-30), kickstarted training improves the data efficiency of new agents, making it significantly easier to iterate on their design.

TL;DR: A novel policy update that combines regularized policy optimization with model learning as an auxiliary loss and does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines.