# Locomotion Control on Half Cheetah sigma 0.7 (test)

Source: [Locomotion Control on Half Cheetah sigma 0.7 (test)](<https://www.sota2.com/research/sota/locomotion-control-on-half-cheetah-sigma-0-7-test>)

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

Data updated: 2026-02-26T06:02:15.502Z

Evaluation of locomotion control performance on the Half Cheetah environment configured with sigma 0.7, 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 0.7 (test) |
| Metric | 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

- [Reward](<https://www.sota2.com/research/sota/locomotion-control-on-half-cheetah-sigma-0-7-test.md?metric=Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| TCN | 462 | Not recorded | 68fa5f511e209131ce9e8f64 |
| TCN | 462 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | 453 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | 453 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | 350 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | 350 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | 267 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | 267 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | 250 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | 250 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | 151 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | 151 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP | -142 | Not recorded | 68fa5f511e209131ce9e8f64 |
| TCN | -147 | Not recorded | 68fa5f511e209131ce9e8f64 |
| DMAP-ne | -205 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Simple | -225 | Not recorded | 68fa5f511e209131ce9e8f64 |
| RMA | -307 | Not recorded | 68fa5f511e209131ce9e8f64 |
| Oracle | -375 | Not recorded | 68fa5f511e209131ce9e8f64 |

### TCN

Reward: 462. Result ID: 698bc2617a967eddb77124bf.

[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

Reward: 462. Result ID: 698c645837894ef7d9ce0f29.

[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

Reward: 453. Result ID: 698bc2617a967eddb77124bd.

[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

Reward: 453. Result ID: 698c645837894ef7d9ce0f27.

[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.

### RMA

Reward: 350. Result ID: 698bc2617a967eddb77124bc.

[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

Reward: 350. Result ID: 698c645837894ef7d9ce0f26.

[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

Reward: 267. Result ID: 698bc2617a967eddb77124c1.

[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

Reward: 267. Result ID: 698c645837894ef7d9ce0f2b.

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

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

### Oracle

Reward: 250. Result ID: 698bc2617a967eddb77124c0.

[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

Reward: 250. Result ID: 698c645837894ef7d9ce0f2a.

[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.

### DMAP-ne

Reward: 151. Result ID: 698bc2617a967eddb77124be.

[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

Reward: 151. Result ID: 698c645837894ef7d9ce0f28.

[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.

### DMAP

Reward: -142. Result ID: 698bc2617a967eddb77124b7.

[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.

### TCN

Reward: -147. Result ID: 698bc2617a967eddb77124b9.

[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

Reward: -205. Result ID: 698bc2617a967eddb77124b8.

[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.

### Simple

Reward: -225. Result ID: 698bc2617a967eddb77124bb.

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

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

### RMA

Reward: -307. Result ID: 698bc2617a967eddb77124b6.

[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.

### Oracle

Reward: -375. Result ID: 698bc2617a967eddb77124ba.

[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.
