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.

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

PDF) Alpha-T: Learning to Traverse over Graphs with An AlphaZero-inspired Self-Play Framework

All Categories - Miles Brundage

State of AI Report 2023 - Air Street Capital

Mastering Atari Games with Limited Data – arXiv Vanity

Warm-start Reinforcement Learning Mobility Science Automation and Inclusion Center

All Categories - Miles Brundage

Summaries from arXiv e-Print archive on

deep learning – Severely Theoretical

Kristian Kersting

deep learning – Severely Theoretical

Kristian Kersting

PDF) Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems

Memory for Lean Reinforcement Learning.pdf