OpenCodePapers

atari-games-on-atari-games

Video GamesAtari Games
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeMean Human Normalized ScoreMedium Human-Normalized ScoreModelNameReleaseDate
Generalized Data Distribution Iteration9620.33%1146.39%GDI-H32022-06-07
Generalized Data Distribution Iteration7810.1%832.5%GDI-I32022-06-07
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link4996.20%MuZero2019-11-19
First return, then explore✓ Link4989.94%Go-Explore2020-04-27
Agent57: Outperforming the Atari Human Benchmark✓ Link4763.69%Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link3374.31%R2D22019-05-01
Never Give Up: Learning Directed Exploration Strategies✓ Link3169.90%NGU2020-02-14
Off-Policy Actor-Critic with Shared Experience Replay1741.36%LASER2019-09-25
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link957.34%IMPALA, deep2018-02-05
Rainbow: Combining Improvements in Deep Reinforcement Learning✓ Link873.97%Rainbow DQN2017-10-06
Mastering Atari with Discrete World Models✓ Link631.17%DreamerV22020-10-05
Model-Based Reinforcement Learning for Atari✓ Link25.3%SimPLe2019-03-01
Check out how to contribute new results.