# Reinforcement Learning on Gymnasium HumanoidStandup

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

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

Data updated: 2026-03-16T08:59:07.602Z

Evaluation of Reinforcement Learning performance on the Gymnasium HumanoidStandup environment, measured by 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) | Gymnasium HumanoidStandup |
| Metric | Episodic 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

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

## Recorded results

| Method | Episodic Return | Result date | Report paper |
| --- | --- | --- | --- |
| CAPO | 149000 | Not recorded | 69b78e590636e5bf4afbda08 |
| Best-of-K | 145000 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO | 143000 | Not recorded | 69b78e590636e5bf4afbda08 |
| CAPO-Avg | 141000 | Not recorded | 69b78e590636e5bf4afbda08 |
| TRPO | 134000 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO-SWA | 121000 | Not recorded | 69b78e590636e5bf4afbda08 |
| PPO-K× | 104000 | Not recorded | 69b78e590636e5bf4afbda08 |

### CAPO

Episodic Return: 149000. Result ID: 69b7c56147f34ce9249f8c95.

[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":"1M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### Best-of-K

Episodic Return: 145000. Result ID: 69b7c56147f34ce9249f8c91.

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

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"1M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### PPO

Episodic Return: 143000. Result ID: 69b7c56147f34ce9249f8c8f.

[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":"1M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### CAPO-Avg

Episodic Return: 141000. Result ID: 69b7c56147f34ce9249f8c94.

[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":"1M","Seeds":"8","Compute-matched":"true"}. This record does not assert independent reproduction.

### TRPO

Episodic Return: 134000. Result ID: 69b7c56147f34ce9249f8c93.

[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":"1M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### PPO-SWA

Episodic Return: 121000. Result ID: 69b7c56147f34ce9249f8c92.

[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":"1M","Seeds":"8","Compute-matched":"false"}. This record does not assert independent reproduction.

### PPO-K×

Episodic Return: 104000. Result ID: 69b7c56147f34ce9249f8c90.

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

Recorded evaluation configuration: {"Backbone":"(64, 64) MLP","Training steps":"1M","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.
