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

halfcheetah dataset and benchmarks – Page 2 · SOTA2 Research

Research Datasets

halfcheetah

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Offline Reinforcement Learning

HalfCheetah kinematic shifts

79.6Score

16

Offline Reinforcement Learning

HalfCheetah Gym-MuJoCo Medium-Replay D4RL

48.9Normalized Score

16

Offline Reinforcement Learning

Halfcheetah

7,357.5Average Return

16

Offline Reinforcement Learning

halfcheetah medium-replay v2

51.2Normalized Score

14

Reinforcement Learning

HalfCheetah v4

10,554Max Return

14

Cross-Domain Offline Policy Adaptation

halfcheetah med Source Target

69.7Normalized Score

14

Offline Policy Adaptation

halfcheetah medium-expert

42.5Normalized Score

14

Offline Reinforcement Learning

HalfCheetah random

33.8Normalized Score

14

Reinforcement Learning

HalfCheetah v5

1Average AUC (z-scored)

13

Reinforcement Learning

HalfCheetah Random

103.45Avg Normalized Score

13

Reinforcement Learning

HalfCheetah delta=[0.2^3, 0.5^3], kappa=2.5 v5 (test)

4,329Return

12

Continuous Control

Halfcheetah

0.03Robustness Gap

12

Continuous Control

HalfCheetah v4

11,672.74Max Average Return

12

Continuous Control

HalfCheetah v5

1.05Normalized Mean Return

12

Offline Reinforcement Learning

HalfCheetah Expert

1,002.09Episodic Return

12

Reinforcement Learning

HalfCheetah fixed linear adversary

7,495Average Performance

12

Worst-case time-constrained reinforcement learning

HalfCheetah MuJoCo (test)

2.76Normalized Worst-Case Reward

12

Robust Reinforcement Learning

HalfCheetah fixed exponential adversary MuJoCo

8,256Avg Performance

12

Continuous Control

HalfCheetah MuJoCo (test)

7,526Worst-case Performance

12

Robot Locomotion

HalfCheetah v1 (test)

4,273.31Score

12

Imitation Learning

HalfCheetah one-shot v2

5.6Normalized Score

11

Reinforcement Learning

HalfCheetah vel

-38.6Average Episode Return

10

HalfCheetah v4

15,789.8Mean Episode Return

10

HalfCheetah

6.11Relative Return Improvement

10

Continuous Control

HalfCheetah v3

9,832Average Return

10

Page 2 of 8

Popular tasks

Offline Reinforcement Learning Reinforcement Learning Continuous Control Locomotion Offline Policy Adaptation

Follow for updates

Join SOTA2 Contact