# Offline Reinforcement Learning on Walker2D Medium-Replay 1T10S Source: [Offline Reinforcement Learning on Walker2D Medium-Replay 1T10S]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.136Z Evaluation of Offline Reinforcement Learning performance using the Walker2D environment with the Medium-Replay 1T10S dataset configuration. 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-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 | | --- | --- | --- | --- | | REAG\*MV | 87.491 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 87.292 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 82.363 | Not recorded | 68fa757c1e209131cea684c9 | | QT | 82.139 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 79.795 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 76.169 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 73.708 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 73.664 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 67.565 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 67.032 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 66.658 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 62.226 | Not recorded | 68fa757c1e209131cea684c9 | | DT | 58.255 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 55.722 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*Dara | 55.438 | Not recorded | 68fa757c1e209131cea684c9 | | Reinformer | 54.801 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 50.296 | Not recorded | 68fa757c1e209131cea684c9 | | REAG\*MV | 47.591 | Not recorded | 68fa757c1e209131cea684c9 | ### REAG\*MV Average Return: 87.491. Result ID: 69a847db6dbb7075b94f35eb. [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: 87.292. Result ID: 69a847db6dbb7075b94f35e8. [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: 82.363. Result ID: 69a847db6dbb7075b94f35f4. [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: 82.139. Result ID: 69a847db6dbb7075b94f35f1. [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: 79.795. Result ID: 69a847db6dbb7075b94f35f7. [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: 76.169. Result ID: 69a847db6dbb7075b94f35ee. [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: 73.708. Result ID: 69a847db6dbb7075b94f35e9. [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: 73.664. Result ID: 69a847db6dbb7075b94f35e6. [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: 67.565. Result ID: 69a847db6dbb7075b94f35ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"DT"}. This record does not assert independent reproduction. ### Reinformer Average Return: 67.032. Result ID: 69a847db6dbb7075b94f35e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 66.658. Result ID: 69a847db6dbb7075b94f35ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass (BM)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. ### REAG\*Dara Average Return: 62.226. Result ID: 69a847db6dbb7075b94f35f5. [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: 58.255. Result ID: 69a847db6dbb7075b94f35ef. [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: 55.722. Result ID: 69a847db6dbb7075b94f35f2. [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: 55.438. Result ID: 69a847db6dbb7075b94f35f6. [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: 54.801. Result ID: 69a847db6dbb7075b94f35f0. [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: 50.296. Result ID: 69a847db6dbb7075b94f35ea. [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: 47.591. Result ID: 69a847db6dbb7075b94f35f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise (JN)","Base Architecture":"Reinformer"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.