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

Deep Reinforcement Learning research benchmarks · SOTA2 Research

Deep Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Gridworld (test)

74.2Usefulness

4

Apr 21, 2026

Pitfall Atari 2600

12IQM Return

4

Apr 16, 2026

Montezuma's Revenge Atari 2600

0IQM Return

4

Apr 16, 2026

Pong Atari 2600

Spectral Routing

19.8IQM Return

4

Apr 16, 2026

Q*bert Atari 2600

Spectral Routing

8,160IQM Return

4

Apr 16, 2026

Seaquest Atari 2600

Spectral Routing

1,642IQM Return

4

Apr 16, 2026

SpaceInvaders Atari 2600

Spectral Routing

1,028IQM Return

4

Apr 16, 2026

Breakout Atari 2600

Spectral Routing

364IQM Return

4

Apr 16, 2026

Arcade Learning Environment 100K (test)

0.093Median Human Normalized Score

3

Mar 18, 2026

Popular datasets

Pong Breakout Q*bert Seaquest Arcade Learning Environment

Follow for updates

Join SOTA2 Contact