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 7 · SOTA2 Research

Research Datasets

halfcheetah

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

HalfCheetah F=1 (test)

6,540.5Average Reward

5

Offline Reinforcement Learning

halfcheetah jump

4,016.6Average Return

5

Reinforcement Learning Surrogate Modeling

HalfCheetah (HC) (test)

85Reward Ratio

4

Reinforcement Learning

HalfCheetah v4

5,381.07Mean Reward

4

Reinforcement Learning

HalfCheetah discrete-regime, exponential dwell

18,598Mean Return

4

halfcheetah expert v2

106.8Normalized Return

4

Reinforcement Learning

HalfCheetah Meta (train)

9,721Reward

4

Continuous Control

HalfCheetah

4.18Value Estimation MAE

4

Offline Reinforcement Learning

halfcheetah medium-expert-morph

63.9Score

4

Offline Reinforcement Learning

halfcheetah medium-expert-kinematic

57.4Score

4

Offline Reinforcement Learning

halfcheetah expert morph

76.4Score

4

Offline Reinforcement Learning

halfcheetah expert-kinematic

72.2Score

4

Constrained behavior synthesis

HalfCheetah 100 evaluation tasks (test)

98S

4

Offline Reinforcement Learning

HalfCheetah Medium-Replay Delayed Reward D4RL

42.4Score

4

Offline Reinforcement Learning

HalfCheetah Medium Delayed Reward D4RL

42.9Score

4

Reinforcement Learning

HalfCheetah target domain 1.5 density

11,515Reward

4

Reinforcement Learning

HalfCheetah 0.5 gravity (target)

7,559Reward

4

Reinforcement Learning

HalfCheetah 1.5 gravity MuJoCo (test)

6,894Reward

4

Safe Offline Multi-Agent Reinforcement Learning

2halfcheetah medium

0.51Reward

3

HalfCheetah non-stationary MuJoCo

15,369Final Training Reward

3

Offline-to-Online Reinforcement Learning

HalfCheetah D4RL Locomotion

49.37Return (HalfCheetah Random)

3

Robot Co-design

HalfCheetah search phase

1.36D2C Score

3

Noisy Action Robust MDP

Halfcheetah MuJoCo Noisy Action Robust MDP (high randomness)

1,765.71Worst-case Return

3

Noisy Action Robust MDP

Halfcheetah Medium Randomness MuJoCo Noisy Action Robust MDP

1,725.6Worst-case Return

3

Noisy Action Robust MDP

Halfcheetah MuJoCo Noisy Action Robust MDP (low randomness)

1,691.8Worst-case Return

3

Page 7 of 8

Popular tasks

Offline Reinforcement Learning Reinforcement Learning Continuous Control Locomotion Offline Policy Adaptation

Follow for updates

Join SOTA2 Contact