# Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium-Replay) Source: [Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium-Replay)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.597Z Evaluation of Offline Reinforcement Learning performance on the HalfCheetah environment configured with the BodyMass Shift (Medium-Replay) 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-Replay) | | 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 | 42.405 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 42.405 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 41.359 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 41.359 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 41.3 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 41.3 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 32.114 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 32.114 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 31.584 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 31.584 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 27.812 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 27.812 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 26.995 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 26.995 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 24.059 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 24.059 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 20.966 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 20.966 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 42.405. Result ID: 69a847db6dbb7075b94f36fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 42.405. Result ID: 69a847db6dbb7075b94f378b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 41.359. Result ID: 69a847db6dbb7075b94f36fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 41.359. Result ID: 69a847db6dbb7075b94f378c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 41.3. Result ID: 69a847db6dbb7075b94f36fa. [Reporting paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 41.3. Result ID: 69a847db6dbb7075b94f378a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 32.114. Result ID: 69a847db6dbb7075b94f36f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 32.114. Result ID: 69a847db6dbb7075b94f3788. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### 1T10S Average Return: 31.584. Result ID: 69a847db6dbb7075b94f36f7. [Reporting paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 31.584. Result ID: 69a847db6dbb7075b94f3787. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 27.812. Result ID: 69a847db6dbb7075b94f36f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 27.812. Result ID: 69a847db6dbb7075b94f3785. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 26.995. Result ID: 69a847db6dbb7075b94f36f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 26.995. Result ID: 69a847db6dbb7075b94f3789. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 24.059. Result ID: 69a847db6dbb7075b94f36f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 24.059. Result ID: 69a847db6dbb7075b94f3786. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 20.966. Result ID: 69a847db6dbb7075b94f36f4. [Reporting paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 20.966. Result ID: 69a847db6dbb7075b94f3784. [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.