# Offline Reinforcement Learning on Hopper Medium-Replay 1T10S Source: [Offline Reinforcement Learning on Hopper Medium-Replay 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.214Z Evaluation of Offline Reinforcement Learning performance using the Hopper environment with the Medium-Replay 1T10S 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-Replay 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 | | --- | --- | --- | --- | | QT | 93.704 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 93.409 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 83.525 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 82.786 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 77.825 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 76.287 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 69.46 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 66.092 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 64.216 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 61.87 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 60.393 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 52.052 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 51.456 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 43.985 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 41.82 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 27.238 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 20.952 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 17.534 | Not recorded | 68fa757c1e209131cea684c9 | ### QT Average Return: 93.704. Result ID: 69a847db6dbb7075b94f3627. [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: 93.409. Result ID: 69a847db6dbb7075b94f362a. [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: 83.525. Result ID: 69a847db6dbb7075b94f362b. [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: 82.786. Result ID: 69a847db6dbb7075b94f3624. [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: 77.825. Result ID: 69a847db6dbb7075b94f3628. [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: 76.287. Result ID: 69a847db6dbb7075b94f3621. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### QT Average Return: 69.46. Result ID: 69a847db6dbb7075b94f361e. [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: 66.092. Result ID: 69a847db6dbb7075b94f361f. [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: 64.216. Result ID: 69a847db6dbb7075b94f361c. [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: 61.87. Result ID: 69a847db6dbb7075b94f3625. [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: 60.393. Result ID: 69a847db6dbb7075b94f3622. [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: 52.052. Result ID: 69a847db6dbb7075b94f362c. [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: 51.456. Result ID: 69a847db6dbb7075b94f362d. [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: 43.985. Result ID: 69a847db6dbb7075b94f3629. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### Reinformer Average Return: 41.82. Result ID: 69a847db6dbb7075b94f3626. [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: 27.238. Result ID: 69a847db6dbb7075b94f3623. [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: 20.952. Result ID: 69a847db6dbb7075b94f3620. [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: 17.534. Result ID: 69a847db6dbb7075b94f361d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.