# Reinforcement Learning on DMControl Reacher easy (100k steps)

Source: [Reinforcement Learning on DMControl Reacher easy (100k steps)](<https://www.sota2.com/research/sota/reinforcement-learning-on-dmcontrol-reacher-easy-100k-steps>)

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

Data updated: 2026-02-26T06:07:28.187Z

Evaluation of Reinforcement Learning performance in the DMControl Reacher easy environment using 100k steps of data, measured by Total 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 | Reinforcement Learning |
| Dataset (including any stated split) | DMControl Reacher easy (100k steps) |
| Metric | Total Reward |
| 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

- [Total Reward](<https://www.sota2.com/research/sota/reinforcement-learning-on-dmcontrol-reacher-easy-100k-steps.md?metric=Total%20Reward>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Total Reward | Result date | Report paper |
| --- | --- | --- | --- |
| ReCoRe | 982 | Not recorded | 68fa72ba1e209131cea58315 |
| RAD | 826 | Not recorded | 68fa72ba1e209131cea58315 |
| CURL | 538 | Not recorded | 68fa72ba1e209131cea58315 |
| ReCoRe | 327 | Not recorded | 68fa72ba1e209131cea58315 |
| Dreamer | 314 | Not recorded | 68fa72ba1e209131cea58315 |
| SAC+AE | 274 | Not recorded | 68fa72ba1e209131cea58315 |
| Pixel SAC | 145 | Not recorded | 68fa72ba1e209131cea58315 |

### ReCoRe

Total Reward: 982. Result ID: 699273313a6c3148490f06ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

Recorded evaluation configuration: {"Regularizer":"Segmentation (S)"}. This record does not assert independent reproduction.

### RAD

Total Reward: 826. Result ID: 699273313a6c3148490f06f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d6b2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CURL

Total Reward: 538. Result ID: 699273313a6c3148490f06ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68611e209131cea1b985.md>)

[Implementation](<https://www.github.com/MishaLaskin/curl>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ReCoRe

Total Reward: 327. Result ID: 699273313a6c3148490f06ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

Recorded evaluation configuration: {"Regularizer":"RGB Image (I)"}. This record does not assert independent reproduction.

### Dreamer

Total Reward: 314. Result ID: 699273313a6c3148490f06ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67341e209131cea14bee.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SAC+AE

Total Reward: 274. Result ID: 699273313a6c3148490f06f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ef1e209131cea193cb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Pixel SAC

Total Reward: 145. Result ID: 699273313a6c3148490f06f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea58315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66571e209131cea0fa31.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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