# Locomotion Control on Half Cheetah sigma 0.5 (test)

Source: [Locomotion Control on Half Cheetah sigma 0.5 (test)](<https://www.sota2.com/research/sota/locomotion-control-on-half-cheetah-sigma-0-5-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:42:07.303Z

Evaluation of locomotion control performance on the Half Cheetah environment configured with sigma 0.5, measured on the test split, typically using Episode Reward.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Locomotion Control |
| Dataset (including any stated split) | Half Cheetah sigma 0.5 (test) |
| Metric | Episode Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Episode Reward](<https://www.sota2.com/research/sota/locomotion-control-on-half-cheetah-sigma-0-5-test.md?metric=Episode%20Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Episode Reward | Result date | Report paper |
| --- | --- | --- | --- |
| TCN | 1117 | Not recorded | 68fa5f511e209131ce9e8f64 |
| TCN | 1117 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | 1033 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | 1033 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | 892 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | 892 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | 822 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | 822 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | 787 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | 787 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | 552 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | 552 | Not recorded | 68fa5f511e209131ce9e8f64 |
| TCN | 475 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | 374 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | 216 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | 208 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | 137 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | 100 | Not recorded | 68fa5f511e209131ce9e8f64 |

### TCN

Episode Reward: 1117. Result ID: 698bc2617a967eddb77124b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### TCN

Episode Reward: 1117. Result ID: 698c645837894ef7d9ce0f23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### DMAP

Episode Reward: 1033. Result ID: 698bc2617a967eddb77124b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### DMAP

Episode Reward: 1033. Result ID: 698c645837894ef7d9ce0f21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### Oracle

Episode Reward: 892. Result ID: 698bc2617a967eddb77124b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### Oracle

Episode Reward: 892. Result ID: 698c645837894ef7d9ce0f24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### RMA

Episode Reward: 822. Result ID: 698bc2617a967eddb77124b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### RMA

Episode Reward: 822. Result ID: 698c645837894ef7d9ce0f20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### Simple

Episode Reward: 787. Result ID: 698bc2617a967eddb77124b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### Simple

Episode Reward: 787. Result ID: 698c645837894ef7d9ce0f25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### DMAP-ne

Episode Reward: 552. Result ID: 698bc2617a967eddb77124b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.3"}. This record does not assert independent reproduction.

### DMAP-ne

Episode Reward: 552. Result ID: 698c645837894ef7d9ce0f22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Training Sigma":"0.3"}. This record does not assert independent reproduction.

### TCN

Episode Reward: 475. Result ID: 698bc2617a967eddb77124ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

### DMAP

Episode Reward: 374. Result ID: 698bc2617a967eddb77124ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

### RMA

Episode Reward: 216. Result ID: 698bc2617a967eddb77124aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

### Simple

Episode Reward: 208. Result ID: 698bc2617a967eddb77124af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

### DMAP-ne

Episode Reward: 137. Result ID: 698bc2617a967eddb77124ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

### Oracle

Episode Reward: 100. Result ID: 698bc2617a967eddb77124ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5f511e209131ce9e8f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b0d.md>)

Recorded evaluation configuration: {"Train Sigma":"0.1"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
