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

D4RL Walker dataset and benchmarks · SOTA2 Research

Research Datasets

D4RL Walker

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Offline Reinforcement Learning

D4RL Walker Medium

77.84Reward

10

Offline-to-online Reinforcement Learning

D4RL Walker expert discretized

14.8Online Normalized Score

9

Offline-to-online Reinforcement Learning

D4RL Walker medium discretized

15.9Online Normalised Score

9

Continuous Control

D4RL Walker Medium-Replay

92.32Normalized Score

5

Continuous Control

D4RL Walker Medium-Expert

114.87Normalized Score

5

D4RL Walker Random

50.4Mean Return

5

Reinforcement Learning

D4RL Walker Medium-Expert

100Mean Normalized Return

5

Reinforcement Learning

D4RL Walker Random

47.1Mean Normalized Return

5

Reinforcement Learning

D4RL Walker no right thigh (medium)

3,293Mean Return

4

Reinforcement Learning

D4RL Walker broken right thigh (medium)

3,743Mean Return

4

Reinforcement Learning

D4RL Walker Med-Expert

110.51D4RL Score

2

Reinforcement Learning

D4RL Walker Med-Replay

72.36D4RL Score

2

Popular tasks

Reinforcement Learning Continuous Control Offline-to-Online Reinforcement Learning Offline Reinforcement Learning Locomotion

Follow for updates

Join SOTA2 Contact