# Offline Reinforcement Learning on HalfCheetah JointNoise Shift (Medium) Source: [Offline Reinforcement Learning on HalfCheetah JointNoise Shift (Medium)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.564Z Evaluation of Offline Reinforcement Learning performance on the HalfCheetah environment configured with Joint Noise Shift at the Medium difficulty level. 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 JointNoise 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 | | --- | --- | --- | --- | | 1T10S | 56.213 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 56.213 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 55.026 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 55.026 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 52.394 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 52.394 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 48.404 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 48.404 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 48.274 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 48.274 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 47.833 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 47.833 | Not recorded | 68fa757c1e209131cea684c9 | | 1T10S | 47.725 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 47.725 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 44.149 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 44.149 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 43.009 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 43.009 | Not recorded | 68fa757c1e209131cea684c9 | ### 1T10S Average Return: 56.213. Result ID: 69a847db6dbb7075b94f36f1. [Reporting paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 56.213. Result ID: 69a847db6dbb7075b94f3781. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 55.026. Result ID: 69a847db6dbb7075b94f36f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 55.026. Result ID: 69a847db6dbb7075b94f3783. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 52.394. Result ID: 69a847db6dbb7075b94f36f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 52.394. Result ID: 69a847db6dbb7075b94f3782. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 48.404. Result ID: 69a847db6dbb7075b94f36f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 48.404. Result ID: 69a847db6dbb7075b94f3780. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 48.274. Result ID: 69a847db6dbb7075b94f36ee. [Reporting paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 48.274. Result ID: 69a847db6dbb7075b94f377e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 47.833. Result ID: 69a847db6dbb7075b94f36ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 47.833. Result ID: 69a847db6dbb7075b94f377d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_Dara"}. This record does not assert independent reproduction. ### 1T10S Average Return: 47.725. Result ID: 69a847db6dbb7075b94f36eb. [Reporting paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 47.725. Result ID: 69a847db6dbb7075b94f377b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"1T10S"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 44.149. Result ID: 69a847db6dbb7075b94f36ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 44.149. Result ID: 69a847db6dbb7075b94f377c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 43.009. Result ID: 69a847db6dbb7075b94f36ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 43.009. Result ID: 69a847db6dbb7075b94f377f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Augmentation Strategy":"REAG\_MV"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.