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.

deep learning – Severely Theoretical

Tags

Mastering Atari Games with Limited Data – arXiv Vanity

deep learning – Severely Theoretical

Aman's AI Journal • Papers List

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

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

State of AI Report 2023 - Air Street Capital

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

Atari 2600 Kangaroo Benchmark (Atari Games)

Memory for Lean Reinforcement Learning.pdf

PDF) Mastering Atari Games with Limited Data

Warm-start Reinforcement Learning Mobility Science Automation and Inclusion Center

Superhuman Performance on the Atari 100K Benchmark: The Power of BBF - A New Value-Based RL Agent from Google DeepMind, Mila, and Universite de Montreal - MarkTechPost