# Offline Reinforcement Learning on walker2d medium-replay v2

Source: [Offline Reinforcement Learning on walker2d medium-replay v2](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-walker2d-medium-replay-v2>)

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

Data updated: 2026-02-26T06:02:13.860Z

Evaluation of Offline Reinforcement Learning performance using the walker2d environment with the medium-replay v2 dataset configuration.

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 | Offline Reinforcement Learning |
| Dataset (including any stated split) | walker2d medium-replay v2 |
| Metric | Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/offline-reinforcement-learning-on-walker2d-medium-replay-v2.md?metric=Return>): Higher is better; unit: SCALAR.

- [OOD](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-walker2d-medium-replay-v2.md?metric=OOD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Return | Result date | Report paper |
| --- | --- | --- | --- |
| LRT+Q | 375 | Not recorded | 6902f0f63ef7ccd74e5e4314 |
| Q | 373 | Not recorded | 6902f0f63ef7ccd74e5e4314 |
| LRT | 315 | Not recorded | 6902f0f63ef7ccd74e5e4314 |

### LRT+Q

Return: 375. Result ID: 699afd685698665ec48f1e16.

[Reporting paper](<https://www.sota2.com/research/paper/6902f0f63ef7ccd74e5e4314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6902f0f63ef7ccd74e5e4314.md>)

Recorded evaluation configuration: {"Mode":"lrt+q"}. This record does not assert independent reproduction.

### Q

Return: 373. Result ID: 699afd685698665ec48f1e15.

[Reporting paper](<https://www.sota2.com/research/paper/6902f0f63ef7ccd74e5e4314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e868.md>)

Recorded evaluation configuration: {"Mode":"q"}. This record does not assert independent reproduction.

### LRT

Return: 315. Result ID: 699afd685698665ec48f1e14.

[Reporting paper](<https://www.sota2.com/research/paper/6902f0f63ef7ccd74e5e4314.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6902f0f63ef7ccd74e5e4314.md>)

Recorded evaluation configuration: {"Mode":"lrt"}. This record does not assert independent reproduction.

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