# Offline Reinforcement Learning on 1T10S HalfCheetah (Medium-Expert) Source: [Offline Reinforcement Learning on 1T10S HalfCheetah (Medium-Expert)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:29.084Z Evaluation of Offline Reinforcement Learning performance using the 1T10S HalfCheetah dataset configured at the Medium-Expert difficulty level, measured by Score. 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 HalfCheetah (Medium-Expert) | | 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 | | --- | --- | --- | --- | | D-AWR | 89.22 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 89.201 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 88.647 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 88.155 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 84.21 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 84.09 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 82.476 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 78.093 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 71.007 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 63.465 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 62.665 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 62.486 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 61.771 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 61.104 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 60.23 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 60.014 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 58.192 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 56.616 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 54.63 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 51.04 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 48.192 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 48.112 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 8.789 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 4.356 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 3.195 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 2.948 | Not recorded | 68fa757c1e209131cea684c9 | ### D-AWR Score: 89.22. Result ID: 69a847db6dbb7075b94f35cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-AWR Score: 89.201. Result ID: 69a847db6dbb7075b94f35c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### AWR Score: 88.647. Result ID: 69a847db6dbb7075b94f35c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### AWR Score: 88.155. Result ID: 69a847db6dbb7075b94f35bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-CQL Score: 84.21. Result ID: 69a847db6dbb7075b94f35cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### CQL Score: 84.09. Result ID: 69a847db6dbb7075b94f35ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### DFDT Score: 82.476. Result ID: 69a847db6dbb7075b94f35d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### DFDT Score: 78.093. Result ID: 69a847db6dbb7075b94f35c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-BCQ Score: 71.007. Result ID: 69a847db6dbb7075b94f35ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BCQ Score: 63.465. Result ID: 69a847db6dbb7075b94f35c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-CQL Score: 62.665. Result ID: 69a847db6dbb7075b94f35c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BCQ Score: 62.486. Result ID: 69a847db6dbb7075b94f35c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BCQ Score: 61.771. Result ID: 69a847db6dbb7075b94f35bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### CQL Score: 61.104. Result ID: 69a847db6dbb7075b94f35bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### H2O Score: 60.23. Result ID: 69a847db6dbb7075b94f35d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-MOPO Score: 60.014. Result ID: 69a847db6dbb7075b94f35d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### H2O Score: 58.192. Result ID: 69a847db6dbb7075b94f35c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-MOPO Score: 56.616. Result ID: 69a847db6dbb7075b94f35c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Score: 54.63. Result ID: 69a847db6dbb7075b94f35cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### MOPO Score: 51.04. Result ID: 69a847db6dbb7075b94f35be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### IGDF Score: 48.192. Result ID: 69a847db6dbb7075b94f35d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### IGDF Score: 48.112. Result ID: 69a847db6dbb7075b94f35c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-BEAR Score: 8.789. Result ID: 69a847db6dbb7075b94f35cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BEAR Score: 4.356. Result ID: 69a847db6dbb7075b94f35ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BEAR Score: 3.195. Result ID: 69a847db6dbb7075b94f35c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Score: 2.948. Result ID: 69a847db6dbb7075b94f35bf. [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.