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

Reinforcement Learning research benchmarks – Page 31 · SOTA2 Research

Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

95.2Normalized Return

4

Feb 26, 2026

92.4Normalized Return

4

Feb 26, 2026

half-cheetah 10-p

80.5Normalized Return

4

Feb 26, 2026

half-cheetah 2-p

44.9Normalized Return

4

Feb 26, 2026

half-cheetah 4-p

54.7Normalized Return

4

Feb 26, 2026

0.927Normalized Return

4

Feb 26, 2026

146.1Normalized Return

4

Feb 26, 2026

136Normalized Return

4

Feb 26, 2026

102Normalized Return

4

Feb 26, 2026

130.6Normalized Return

4

Feb 26, 2026

94.2Normalized Return

4

Feb 26, 2026

94.5Normalized Return

4

Feb 26, 2026

106Normalized Return

4

Feb 26, 2026

99Normalized Return

4

Feb 26, 2026

Reacher target domain 1.5 density

-7.1Reward

4

Feb 26, 2026

Walker2d 1.5 density (target domain)

3,383Reward

4

Feb 26, 2026

Ant target domain 1.5 density

6,036Reward

4

Feb 26, 2026

HalfCheetah target domain 1.5 density

11,515Reward

4

Feb 26, 2026

Reacher target 0.5 gravity

Optimal in Target

-7.2Reward

4

Feb 26, 2026

Walker2d 0.5 gravity (target)

Optimal in Target

2,830Reward

4

Feb 26, 2026

Ant 0.5 gravity (target)

Optimal in Target

3,380Total Reward

4

Feb 26, 2026

HalfCheetah 0.5 gravity (target)

Optimal in Target

7,559Reward

4

Feb 26, 2026

Reacher 1.5 gravity MuJoCo (test)

Optimal in Target

-8.3Reward

4

Feb 26, 2026

Walker2d 1.5 gravity MuJoCo (test)

4,409Reward

4

Feb 26, 2026

Ant 1.5 gravity MuJoCo (test)

Optimal in Target

5,320Reward

4

Feb 26, 2026

Page 31 of 41

Popular datasets

Atari Atari 2600 halfcheetah DMControl hopper

Follow for updates

Join SOTA2 Contact