RL Weekly 36: AlphaZero with a Learned Model achieves SotA in Atari

In this issue, we look at MuZero, DeepMind’s new algorithm that learns a model and achieves AlphaZero performance in Chess, Shogi, and Go and achieves state-of-the-art performance on Atari. We also look at Safety Gym, OpenAI’s new environment suite for safe RL.

EfficientZero: Mastering Atari Games with Limited Data (Machine Learning Research Paper Explained)

UC Berkeley Reward-Free RL Beats SOTA Reward-Based RL

Scheduling UAV Swarm with Attention-based Graph Reinforcement Learning for Ground-to-air Heterogeneous Data Communication

RL Weekly 37: Observational Overfitting, Hindsight Credit Assignment, and Procedurally Generated Environment Suite

Kristian Kersting

Mastering Atari Games with Limited Data – arXiv Vanity

Kristian Kersting

Kristian Kersting

AlphaGo/AlphaGoZero/AlphaZero/MuZero: Mastering games using progressively fewer priors

2008.06495] Joint Policy Search for Multi-agent Collaboration with Imperfect Information

PDF) Tensor Implementation of Monte-Carlo Tree Search for Model-Based Reinforcement Learning

Mastering Atari Games with Limited Data – arXiv Vanity