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 20 · SOTA2 Research

Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AntMaze umaze-diverse v2

73.4Initial Score

6

Feb 26, 2026

DMControl cartpole-swingup (expert)

20.43Averaged Normalized Score

6

Feb 26, 2026

DMControl finger-spin (expert)

98.42Averaged Normalized Score

6

Feb 26, 2026

DMControl reacher-easy (expert)

58.19Averaged Normalized Score

6

Feb 26, 2026

DMControl ball-in-cup-catch (expert)

38.87Avg Normalized Score

6

Feb 26, 2026

DMControl walker-walk (expert)

97.97Averaged Normalized Score

6

Feb 26, 2026

DMControl cheetah-run (expert)

96.28Avg Normalized Score

6

Feb 26, 2026

DMControl cartpole-swingup (mixed)

16.36Avg Normalized Score

6

Feb 26, 2026

DMControl finger-spin (mixed)

98.54Avg Normalized Score

6

Feb 26, 2026

DMControl reacher-easy (mixed)

75.61Avg Normalized Score

6

Feb 26, 2026

DMControl ball-in-cup-catch (mixed)

51.28Averaged Normalized Score

6

Feb 26, 2026

DMControl walker-walk (mixed)

97.84Avg Normalized Score

6

Feb 26, 2026

DMControl cheetah-run (mixed)

93.16Avg Normalized Score

6

Feb 26, 2026

DMControl cartpole-swingup (random)

38.59Avg Normalized Score

6

Feb 26, 2026

DMControl finger-spin (random)

30.24Averaged Normalized Score

6

Feb 26, 2026

DMControl reacher-easy (random)

85.76Avg Normalized Score

6

Feb 26, 2026

DMControl ball-in-cup-catch (random)

92.81Normalized Score

6

Feb 26, 2026

DMControl walker-walk (random)

18.23Avg Normalized Score

6

Feb 26, 2026

MuJoCo Humanoid v2 (test)

9,080.54Max Avg Return

6

Feb 26, 2026

MuJoCo Humanoid-Standup v2 (test)

267,734.03Max Average Return

6

Feb 26, 2026

Delayed MuJoCo Ant v2 (test)

4,851.64Max Average Return

6

Feb 26, 2026

Delayed MuJoCo Walker2d v2 (test)

5,274.89Max Average Return

6

Feb 26, 2026

Delayed MuJoCo HalfCheetah v2 (test)

8,451.2Average Return

6

Feb 26, 2026

Delayed MuJoCo Hopper v2 (test)

3,435.28Max Return

6

Feb 26, 2026

Sparse MuJoCo Ant v2 (test)

973.6Max Average Return

6

Feb 26, 2026

Page 20 of 41

Popular datasets

Atari Atari 2600 halfcheetah DMControl hopper

Follow for updates

Join SOTA2 Contact