# Offline Reinforcement Learning on 1T10S Hopper (Medium-Replay) Source: [Offline Reinforcement Learning on 1T10S Hopper (Medium-Replay)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:28.942Z Evaluation of Offline Reinforcement Learning performance using the 1T10S Hopper dataset configuration with Medium-Replay settings. 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 Hopper (Medium-Replay) | | Metric | 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 - [Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | H2O | 98.988 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 97.538 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 95.655 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 95.23 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 74.72 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 74.72 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 68.163 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 66.455 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 65.103 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 64.519 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 64.519 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 64.168 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 63.937 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 63.178 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 61.302 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 55.607 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 44.883 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 37.821 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 6.282 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 6.147 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 5.637 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 5.504 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 5.498 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 5.482 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 2.619 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 1.841 | Not recorded | 68fa757c1e209131cea684c9 | ### H2O Score: 98.988. Result ID: 69a847db6dbb7075b94f356a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### H2O Score: 97.538. Result ID: 69a847db6dbb7075b94f355d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### IGDF Score: 95.655. Result ID: 69a847db6dbb7075b94f355e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### IGDF Score: 95.23. Result ID: 69a847db6dbb7075b94f356b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### DFDT Score: 74.72. Result ID: 69a847db6dbb7075b94f355c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### DFDT Score: 74.72. Result ID: 69a847db6dbb7075b94f3569. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-CQL Score: 68.163. Result ID: 69a847db6dbb7075b94f355a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### CQL Score: 66.455. Result ID: 69a847db6dbb7075b94f3555. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BCQ Score: 65.103. Result ID: 69a847db6dbb7075b94f3561. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BCQ Score: 64.519. Result ID: 69a847db6dbb7075b94f3554. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-BCQ Score: 64.519. Result ID: 69a847db6dbb7075b94f3566. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BCQ Score: 64.168. Result ID: 69a847db6dbb7075b94f3559. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-AWR Score: 63.937. Result ID: 69a847db6dbb7075b94f3565. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-CQL Score: 63.178. Result ID: 69a847db6dbb7075b94f3567. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### CQL Score: 61.302. Result ID: 69a847db6dbb7075b94f3562. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### AWR Score: 55.607. Result ID: 69a847db6dbb7075b94f3553. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-AWR Score: 44.883. Result ID: 69a847db6dbb7075b94f3558. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### AWR Score: 37.821. Result ID: 69a847db6dbb7075b94f3560. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BEAR Score: 6.282. Result ID: 69a847db6dbb7075b94f3552. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-MOPO Score: 6.147. Result ID: 69a847db6dbb7075b94f3568. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Score: 5.637. Result ID: 69a847db6dbb7075b94f3564. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### MOPO Score: 5.504. Result ID: 69a847db6dbb7075b94f3556. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Score: 5.498. Result ID: 69a847db6dbb7075b94f3563. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-MOPO Score: 5.482. Result ID: 69a847db6dbb7075b94f355b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-BEAR Score: 2.619. Result ID: 69a847db6dbb7075b94f3557. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BEAR Score: 1.841. Result ID: 69a847db6dbb7075b94f355f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.