# Offline Reinforcement Learning on Walker2D Medium 1T10S Source: [Offline Reinforcement Learning on Walker2D Medium 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.111Z Evaluation of Offline Reinforcement Learning performance on the specific Walker2D environment configuration known as Medium 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 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 | 84.582 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 84.325 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 83.068 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 82.354 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 80.904 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 80.857 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 80.857 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 80.666 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 80.621 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 78.768 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 78.672 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 78.257 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 75.008 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 75.008 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 74.748 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 74.268 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 71.779 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 71.068 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 84.582. Result ID: 69a847db6dbb7075b94f35d9. [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: 84.325. Result ID: 69a847db6dbb7075b94f35d6. [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: 83.068. Result ID: 69a847db6dbb7075b94f35dc. [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: 82.354. Result ID: 69a847db6dbb7075b94f35d8. [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: 80.904. Result ID: 69a847db6dbb7075b94f35e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"QT"}. This record does not assert independent reproduction. ### Reinformer Average Return: 80.857. Result ID: 69a847db6dbb7075b94f35d5. [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: 80.857. Result ID: 69a847db6dbb7075b94f35d7. [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: 80.666. Result ID: 69a847db6dbb7075b94f35db. [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: 80.621. Result ID: 69a847db6dbb7075b94f35df. [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: 78.768. Result ID: 69a847db6dbb7075b94f35d4. [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: 78.672. Result ID: 69a847db6dbb7075b94f35e5. [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: 78.257. Result ID: 69a847db6dbb7075b94f35da. [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: 75.008. Result ID: 69a847db6dbb7075b94f35e0. [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: 75.008. Result ID: 69a847db6dbb7075b94f35e1. [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: 74.748. Result ID: 69a847db6dbb7075b94f35de. [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: 74.268. Result ID: 69a847db6dbb7075b94f35e4. [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: 71.779. Result ID: 69a847db6dbb7075b94f35e3. [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: 71.068. Result ID: 69a847db6dbb7075b94f35dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"DT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.