Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Atari dataset and benchmarks · SOTA2 Research

Research Datasets

Atari

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Reinforcement Learning

Atari 100k

7,128Alien Score

50

Reinforcement Learning

Atari100k (test)

7,127.7Alien Score

23

Reinforcement Learning

Atari 100K (test)

2.791Mean Score

21

Reinforcement Learning

Atari 57

3,824,506.3Atlantis

21

Reinforcement Learning

Atari 100k steps (test)

0.809Median HNS

20

Reinforcement Learning

Atari-57 (test)

2,041.12Median Human Norm Return

15

Reinforcement Learning

Atari 2600

7,127.7Alien Score

15

Reinforcement Learning

Atari 7-game suite ALE (test)

4.815Relative Score

13

Reinforcement Learning

Atari-57 (full)

22HWRB

13

Atari Game Playing

Atari 57 games 200M environment frames

1,047Median Human-Normalized Score

11

Reinforcement Learning

Atari 57 full suite 2600

57Games Above Human Count

11

Reinforcement Learning

Atari Space Invaders

54,500Mean Episode Return

11

Visual Reinforcement Learning

Atari 10

2,408Assault Score

10

Reinforcement Learning

55 Atari games

1,160Mean Human-Normalized Score

10

Atari Games Performance

Atari 100k

1Mean Score (HNS)

10

Reinforcement Learning

Atari 10 hard-exploration games (train)

124,524.02Alien Score

10

Reinforcement Learning

Atari (test)

1.1Fraction of Teacher Score

9

Continual Offline Reinforcement Learning

Atari Breakout-Alien-Atlantis-Boxing-Centipede sequence 5-task continual offline (final performance)

114Breakout Score

9

Continual Learning

Atari Normalized continual learning

2.38Max Performance

9

Reinforcement Learning

Atari 100k steps (overall)

91.6Game Score: Boxing

9

Reinforcement Learning

Atari Human Normalized 40M frames

1.25Mean Return

9

Reinforcement Learning

Atari 57 (ALE) 200M frames sticky actions

1,047Median Human-Normalized Score

9

Reinforcement Learning

Atari 26 100K environment steps

7,127.7Alien Score

9

Reinforcement Learning

Atari 26 Game Subset

47.5Median Score

9

Reinforcement Learning

Atari 20 (final)

1.219IQM Score

8

Page 1 of 4

PreviousNext

Popular tasks

Reinforcement Learning Atari Game Playing Continual Reinforcement Learning Adversarial Attack Game Playing

Follow for updates

Join SOTA2 Contact