# Reinforcement Learning on Gymnasium Humanoid

Source: [Reinforcement Learning on Gymnasium Humanoid](<https://www.sota2.com/research/sota/reinforcement-learning-on-gymnasium-humanoid>)

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

Data updated: 2026-03-16T08:59:07.567Z

Evaluation of Reinforcement Learning performance on the Gymnasium Humanoid continuous control environment, measured by cumulative 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) | Gymnasium Humanoid |
| Metric | Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Return](<https://www.sota2.com/research/sota/reinforcement-learning-on-gymnasium-humanoid.md?metric=Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Return | Result date | Report paper |
| --- | --- | --- | --- |
| CAPO | 6367 | Not recorded | 69b78e590636e5bf4afbda08 |
| TRPO | 3730 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO-SWA | 750 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO | 739 | Not recorded | 69b78e590636e5bf4afbda08 |
| Best-of-K | 716 | Not recorded | 69b78e590636e5bf4afbda08 |
| CAPO-Avg | 696 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO-K× | 429 | Not recorded | 69b78e590636e5bf4afbda08 |

### CAPO

Return: 6367. Result ID: 69b7c56147f34ce9249f8c8e.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### TRPO

Return: 3730. Result ID: 69b7c56147f34ce9249f8c8c.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634f1e209131ce9fe056.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### PPO-SWA

Return: 750. Result ID: 69b7c56147f34ce9249f8c8b.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65651e209131cea09f96.md>)

[Implementation](<https://github.com/timgaripov/swa>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### PPO

Return: 739. Result ID: 69b7c56147f34ce9249f8c88.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63a01e209131ce9ffdaa.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### Best-of-K

Return: 716. Result ID: 69b7c56147f34ce9249f8c8a.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### CAPO-Avg

Return: 696. Result ID: 69b7c56147f34ce9249f8c8d.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### PPO-K×

Return: 429. Result ID: 69b7c56147f34ce9249f8c89.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e590636e5bf4afbda08.md>)

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"4M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

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