# Offline Reinforcement Learning on Walker2D Medium-Expert 1T10S Source: [Offline Reinforcement Learning on Walker2D Medium-Expert 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.165Z Evaluation of Offline Reinforcement Learning performance on the specific Walker2D environment configuration known as Medium-Expert 1T10S, 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) | Walker2D 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 | 118.564 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 118.218 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 117.765 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 117.36 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 116.149 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 116.115 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 115.746 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 111.236 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 111.06 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 94.578 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 93.082 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 92.744 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 88.235 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 85.328 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 84.897 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 84.43 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 83.761 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 83.388 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 118.564. Result ID: 69a847db6dbb7075b94f3606. [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: 118.218. Result ID: 69a847db6dbb7075b94f3605. [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: 117.765. Result ID: 69a847db6dbb7075b94f3608. [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: 117.36. Result ID: 69a847db6dbb7075b94f3602. [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: 116.149. Result ID: 69a847db6dbb7075b94f3603. [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: 116.115. Result ID: 69a847db6dbb7075b94f3609. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### DT Average Return: 115.746. Result ID: 69a847db6dbb7075b94f3601. [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: 111.236. Result ID: 69a847db6dbb7075b94f3607. [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: 111.06. Result ID: 69a847db6dbb7075b94f3604. [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: 94.578. Result ID: 69a847db6dbb7075b94f3600. [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: 93.082. Result ID: 69a847db6dbb7075b94f35fa. [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: 92.744. Result ID: 69a847db6dbb7075b94f35fd. [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: 88.235. Result ID: 69a847db6dbb7075b94f35fb. [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: 85.328. Result ID: 69a847db6dbb7075b94f35fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### REAG\*MV Average Return: 84.897. Result ID: 69a847db6dbb7075b94f35fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### DT Average Return: 84.43. Result ID: 69a847db6dbb7075b94f35f8. [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: 83.761. Result ID: 69a847db6dbb7075b94f35ff. [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: 83.388. Result ID: 69a847db6dbb7075b94f35f9. [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.