# Reinforcement Learning on MuJoCo HalfCheetah v5

Source: [Reinforcement Learning on MuJoCo HalfCheetah v5](<https://www.sota2.com/research/sota/reinforcement-learning-on-mujoco-halfcheetah-v5>)

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

Data updated: 2026-03-04T14:22:44.686Z

Evaluation of standard Reinforcement Learning performance on the MuJoCo HalfCheetah environment, version 5, typically measured by Mean episodic return.

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 | Reinforcement Learning |
| Dataset (including any stated split) | MuJoCo HalfCheetah v5 |
| Metric | Mean Episodic Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Mean Episodic Return](<https://www.sota2.com/research/sota/reinforcement-learning-on-mujoco-halfcheetah-v5.md?metric=Mean%20Episodic%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Episodic Return | Result date | Report paper |
| --- | --- | --- | --- |
| SAID | 14845 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAC | 12450 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAID | 9648 | Not recorded | 69a66c622d603e6de3e3d20c |
| SADR | 8190 | Not recorded | 69a66c622d603e6de3e3d20c |
| VDPO | 6720 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAID | 5565 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAID | 5289 | Not recorded | 69a66c622d603e6de3e3d20c |
| SADR | 4945 | Not recorded | 69a66c622d603e6de3e3d20c |
| DR | 4702 | Not recorded | 69a66c622d603e6de3e3d20c |
| SADR | 4565 | Not recorded | 69a66c622d603e6de3e3d20c |
| VDPO | 3350 | Not recorded | 69a66c622d603e6de3e3d20c |
| DR | 2873 | Not recorded | 69a66c622d603e6de3e3d20c |
| VDPO | 2085 | Not recorded | 69a66c622d603e6de3e3d20c |
| DR | 1249 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAC | 129 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAC | 121 | Not recorded | 69a66c622d603e6de3e3d20c |
| SAC | 109 | Not recorded | 69a66c622d603e6de3e3d20c |

### SAID

Mean Episodic Return: 14845. Result ID: 69a840326dbb7075b94f04eb.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"0"}. This record does not assert independent reproduction.

### SAC

Mean Episodic Return: 12450. Result ID: 69a840326dbb7075b94f04de.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a51e209131cea05d13.md>)

[Implementation](<https://www.sota2.com/github.com/haarnoja/sac>)

Recorded evaluation configuration: {"Delay steps":"0"}. This record does not assert independent reproduction.

### SAID

Mean Episodic Return: 9648. Result ID: 69a840326dbb7075b94f04ec.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction.

### SADR

Mean Episodic Return: 8190. Result ID: 69a840326dbb7075b94f04e5.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction.

### VDPO

Mean Episodic Return: 6720. Result ID: 69a840326dbb7075b94f04e8.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754d1e209131cea66f46.md>)

Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction.

### SAID

Mean Episodic Return: 5565. Result ID: 69a840326dbb7075b94f04ed.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction.

### SAID

Mean Episodic Return: 5289. Result ID: 69a840326dbb7075b94f04ee.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction.

### SADR

Mean Episodic Return: 4945. Result ID: 69a840326dbb7075b94f04e6.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction.

### DR

Mean Episodic Return: 4702. Result ID: 69a840326dbb7075b94f04e2.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction.

### SADR

Mean Episodic Return: 4565. Result ID: 69a840326dbb7075b94f04e7.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction.

### VDPO

Mean Episodic Return: 3350. Result ID: 69a840326dbb7075b94f04e9.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754d1e209131cea66f46.md>)

Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction.

### DR

Mean Episodic Return: 2873. Result ID: 69a840326dbb7075b94f04e3.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction.

### VDPO

Mean Episodic Return: 2085. Result ID: 69a840326dbb7075b94f04ea.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754d1e209131cea66f46.md>)

Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction.

### DR

Mean Episodic Return: 1249. Result ID: 69a840326dbb7075b94f04e4.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction.

### SAC

Mean Episodic Return: 129. Result ID: 69a840326dbb7075b94f04e0.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a51e209131cea05d13.md>)

[Implementation](<https://www.sota2.com/github.com/haarnoja/sac>)

Recorded evaluation configuration: {"Delay steps":"8"}. This record does not assert independent reproduction.

### SAC

Mean Episodic Return: 121. Result ID: 69a840326dbb7075b94f04e1.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a51e209131cea05d13.md>)

[Implementation](<https://www.sota2.com/github.com/haarnoja/sac>)

Recorded evaluation configuration: {"Delay steps":"16"}. This record does not assert independent reproduction.

### SAC

Mean Episodic Return: 109. Result ID: 69a840326dbb7075b94f04df.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c622d603e6de3e3d20c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64a51e209131cea05d13.md>)

[Implementation](<https://www.sota2.com/github.com/haarnoja/sac>)

Recorded evaluation configuration: {"Delay steps":"4"}. This record does not assert independent reproduction.

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