# Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium) Source: [Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.533Z Evaluation of Offline Reinforcement Learning performance on the HalfCheetah environment configured with the BodyMass Shift (Medium) setting, measured by Average 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 | Offline Reinforcement Learning | | Dataset (including any stated split) | HalfCheetah BodyMass Shift (Medium) | | Metric | Average Return | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Average Return](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Return | Result date | Report paper | | --- | --- | --- | --- | | REAG\*MV | 47.303 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 47.303 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 46.383 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 46.383 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 44.656 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 44.656 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 42.451 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 42.451 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 40.25 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 40.25 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 39.954 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 39.954 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 38.261 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 38.261 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 37.599 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 37.599 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 37.353 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 37.353 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 47.303. Result ID: 69a847db6dbb7075b94f36e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 47.303. Result ID: 69a847db6dbb7075b94f3779. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 46.383. Result ID: 69a847db6dbb7075b94f36ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 46.383. Result ID: 69a847db6dbb7075b94f377a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 44.656. Result ID: 69a847db6dbb7075b94f36e8. [Reporting paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 44.656. Result ID: 69a847db6dbb7075b94f3778. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 42.451. Result ID: 69a847db6dbb7075b94f36e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 42.451. Result ID: 69a847db6dbb7075b94f3776. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 40.25. Result ID: 69a847db6dbb7075b94f36e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 40.25. Result ID: 69a847db6dbb7075b94f3773. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### 1T10S Average Return: 39.954. Result ID: 69a847db6dbb7075b94f36e2. [Reporting paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 39.954. Result ID: 69a847db6dbb7075b94f3772. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 38.261. Result ID: 69a847db6dbb7075b94f36e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 38.261. Result ID: 69a847db6dbb7075b94f3777. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 37.599. Result ID: 69a847db6dbb7075b94f36e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 37.599. Result ID: 69a847db6dbb7075b94f3774. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 37.353. Result ID: 69a847db6dbb7075b94f36e5. [Reporting paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 37.353. Result ID: 69a847db6dbb7075b94f3775. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.