# Offline Reinforcement Learning on Hopper Medium 1T10S Source: [Offline Reinforcement Learning on Hopper Medium 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.190Z Evaluation of Offline Reinforcement Learning performance on the Hopper environment using the 1T10S Medium dataset configuration, 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) | Hopper Medium 1T10S | | 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\*Dara | 78.325 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 73.987 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 72.346 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 70.685 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 70.466 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 70.356 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 70.34 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 68.709 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 68.656 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 62.226 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 59.085 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 51.796 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 51.771 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 51.357 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 49.516 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 39.435 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 37.787 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 34.057 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*Dara Average Return: 78.325. Result ID: 69a847db6dbb7075b94f3619. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 73.987. Result ID: 69a847db6dbb7075b94f3618. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 72.346. Result ID: 69a847db6dbb7075b94f3617. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### DT Average Return: 70.685. Result ID: 69a847db6dbb7075b94f3613. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 70.466. Result ID: 69a847db6dbb7075b94f361a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 70.356. Result ID: 69a847db6dbb7075b94f3616. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### Reinformer Average Return: 70.34. Result ID: 69a847db6dbb7075b94f3614. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 68.709. Result ID: 69a847db6dbb7075b94f361b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 68.656. Result ID: 69a847db6dbb7075b94f3615. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 62.226. Result ID: 69a847db6dbb7075b94f3612. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 59.085. Result ID: 69a847db6dbb7075b94f360e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 51.796. Result ID: 69a847db6dbb7075b94f360f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 51.771. Result ID: 69a847db6dbb7075b94f3611. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 51.357. Result ID: 69a847db6dbb7075b94f360b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### QT Average Return: 49.516. Result ID: 69a847db6dbb7075b94f360c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 39.435. Result ID: 69a847db6dbb7075b94f360d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 37.787. Result ID: 69a847db6dbb7075b94f3610. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 34.057. Result ID: 69a847db6dbb7075b94f360a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"DT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.