# Offline Reinforcement Learning on 1T10S Walker2D (Medium-Replay) Source: [Offline Reinforcement Learning on 1T10S Walker2D (Medium-Replay)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:28.850Z Evaluation of Offline Reinforcement Learning performance using the 1T10S configuration of the Walker2D Medium-Replay dataset. 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) | 1T10S Walker2D (Medium-Replay) | | Metric | Performance Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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 - [Performance Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Performance Score | Result date | Report paper | | --- | --- | --- | --- | | DFDT | 71.67 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 71.236 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 66.834 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 62.494 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 57.432 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 56.11 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 55.228 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 54.753 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 51.742 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 51.447 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 50.714 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 50.714 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 50.601 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 50.6 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 47.033 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 36.807 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 32.008 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 31.623 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 15.389 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 12.129 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 11.563 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 11.379 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 1.078 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 0.474 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 0.384 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 0.067 | Not recorded | 68fa757c1e209131cea684c9 | ### DFDT Performance Score: 71.67. Result ID: 69a847db6dbb7075b94f350e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### DFDT Performance Score: 71.236. Result ID: 69a847db6dbb7075b94f351b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### IGDF Performance Score: 66.834. Result ID: 69a847db6dbb7075b94f351d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### IGDF Performance Score: 62.494. Result ID: 69a847db6dbb7075b94f3510. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-CQL Performance Score: 57.432. Result ID: 69a847db6dbb7075b94f350c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### H2O Performance Score: 56.11. Result ID: 69a847db6dbb7075b94f350f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### H2O Performance Score: 55.228. Result ID: 69a847db6dbb7075b94f351c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### CQL Performance Score: 54.753. Result ID: 69a847db6dbb7075b94f3507. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-CQL Performance Score: 51.742. Result ID: 69a847db6dbb7075b94f3519. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BCQ Performance Score: 51.447. Result ID: 69a847db6dbb7075b94f350b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BCQ Performance Score: 50.714. Result ID: 69a847db6dbb7075b94f3506. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-BCQ Performance Score: 50.714. Result ID: 69a847db6dbb7075b94f3518. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BCQ Performance Score: 50.601. Result ID: 69a847db6dbb7075b94f3513. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### CQL Performance Score: 50.6. Result ID: 69a847db6dbb7075b94f3514. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### AWR Performance Score: 47.033. Result ID: 69a847db6dbb7075b94f3505. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-AWR Performance Score: 36.807. Result ID: 69a847db6dbb7075b94f3517. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-AWR Performance Score: 32.008. Result ID: 69a847db6dbb7075b94f350a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### AWR Performance Score: 31.623. Result ID: 69a847db6dbb7075b94f3512. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-MOPO Performance Score: 15.389. Result ID: 69a847db6dbb7075b94f351a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-MOPO Performance Score: 12.129. Result ID: 69a847db6dbb7075b94f350d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Performance Score: 11.563. Result ID: 69a847db6dbb7075b94f3508. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Performance Score: 11.379. Result ID: 69a847db6dbb7075b94f3515. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Performance Score: 1.078. Result ID: 69a847db6dbb7075b94f3509. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BEAR Performance Score: 0.474. Result ID: 69a847db6dbb7075b94f3511. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Performance Score: 0.384. Result ID: 69a847db6dbb7075b94f3516. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BEAR Performance Score: 0.067. Result ID: 69a847db6dbb7075b94f3504. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.