# Offline Reinforcement Learning on Hopper Medium-Expert 1T10S Source: [Offline Reinforcement Learning on Hopper Medium-Expert 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.237Z Evaluation of Offline Reinforcement Learning performance on the Hopper environment using the Medium-Expert 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-Expert 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\*MV | 109.803 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 109.746 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 109.472 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 109.367 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 109.256 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 109.255 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 109.056 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 108.261 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 108.254 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 77.279 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 73.952 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 73.363 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 68.973 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 64.206 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 61.162 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 52.873 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 33.631 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 33.554 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 109.803. Result ID: 69a847db6dbb7075b94f363c. [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: 109.746. Result ID: 69a847db6dbb7075b94f363f. [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: 109.472. Result ID: 69a847db6dbb7075b94f363b. [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: 109.367. Result ID: 69a847db6dbb7075b94f363a. [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: 109.256. Result ID: 69a847db6dbb7075b94f3638. [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: 109.255. Result ID: 69a847db6dbb7075b94f363e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### QT Average Return: 109.056. Result ID: 69a847db6dbb7075b94f3639. [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: 108.261. Result ID: 69a847db6dbb7075b94f363d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### DT Average Return: 108.254. Result ID: 69a847db6dbb7075b94f3637. [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: 77.279. Result ID: 69a847db6dbb7075b94f3636. [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: 73.952. Result ID: 69a847db6dbb7075b94f3633. [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: 73.363. Result ID: 69a847db6dbb7075b94f3635. [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: 68.973. Result ID: 69a847db6dbb7075b94f362f. [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: 64.206. Result ID: 69a847db6dbb7075b94f3632. [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: 61.162. Result ID: 69a847db6dbb7075b94f3630. [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: 52.873. Result ID: 69a847db6dbb7075b94f3631. [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: 33.631. Result ID: 69a847db6dbb7075b94f3634. [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: 33.554. Result ID: 69a847db6dbb7075b94f362e. [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.