# Offline Reinforcement Learning on Halfcheetah D4RL v2 (offline) Source: [Offline Reinforcement Learning on Halfcheetah D4RL v2 (offline)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:49.274Z Evaluation of Offline Reinforcement Learning performance using the HalfCheetah D4RL v2 dataset configuration, measured by Average 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) | Halfcheetah D4RL v2 (offline) | | Metric | Average Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | UWMSG | 56 | Not recorded | 68fa75871e209131cea6863f | | MSG | 52 | Not recorded | 68fa75871e209131cea6863f | | EDAC | 47.4 | Not recorded | 68fa75871e209131cea6863f | | TRACER | 43.8 | Not recorded | 68fa75871e209131cea6863f | | RIQL | 43.6 | Not recorded | 68fa75871e209131cea6863f | | RIQL | 43.1 | Not recorded | 68fa75871e209131cea6863f | | RIQL | 42.9 | Not recorded | 68fa75871e209131cea6863f | | TRACER | 42.9 | Not recorded | 68fa75871e209131cea6863f | | IQL | 42.3 | Not recorded | 68fa75871e209131cea6863f | | IQL | 42.2 | Not recorded | 68fa75871e209131cea6863f | | TRACER | 40 | Not recorded | 68fa75871e209131cea6863f | | EDAC | 38.6 | Not recorded | 68fa75871e209131cea6863f | | IQL | 36.7 | Not recorded | 68fa75871e209131cea6863f | | BC | 35.8 | Not recorded | 68fa75871e209131cea6863f | | BC | 35.8 | Not recorded | 68fa75871e209131cea6863f | | BC | 35.8 | Not recorded | 68fa75871e209131cea6863f | | UWMSG | 35.6 | Not recorded | 68fa75871e209131cea6863f | | TRACER | 34.2 | Not recorded | 68fa75871e209131cea6863f | | BC | 33.4 | Not recorded | 68fa75871e209131cea6863f | | CQL | 32.6 | Not recorded | 68fa75871e209131cea6863f | | CQL | 29.2 | Not recorded | 68fa75871e209131cea6863f | | RIQL | 27.3 | Not recorded | 68fa75871e209131cea6863f | | IQL | 21.4 | Not recorded | 68fa75871e209131cea6863f | | CQL | 19.9 | Not recorded | 68fa75871e209131cea6863f | | MSG | 17.5 | Not recorded | 68fa75871e209131cea6863f | | CQL | 9 | Not recorded | 68fa75871e209131cea6863f | | UWMSG | 2.9 | Not recorded | 68fa75871e209131cea6863f | | UWMSG | 2.9 | Not recorded | 68fa75871e209131cea6863f | | EDAC | 2.1 | Not recorded | 68fa75871e209131cea6863f | | MSG | 1.7 | Not recorded | 68fa75871e209131cea6863f | | EDAC | 1.5 | Not recorded | 68fa75871e209131cea6863f | | MSG | -0.2 | Not recorded | 68fa75871e209131cea6863f | ### UWMSG Average Score: 56. Result ID: 6993cd6f3a6c31484918a47e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### MSG Average Score: 52. Result ID: 6993cd6f3a6c31484918a47d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### EDAC Average Score: 47.4. Result ID: 6993cd6f3a6c31484918a47c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### TRACER Average Score: 43.8. Result ID: 6993cd6f3a6c31484918a492. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### RIQL Average Score: 43.6. Result ID: 6993cd6f3a6c31484918a489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### RIQL Average Score: 43.1. Result ID: 6993cd6f3a6c31484918a491. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### RIQL Average Score: 42.9. Result ID: 6993cd6f3a6c31484918a481. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### TRACER Average Score: 42.9. Result ID: 6993cd6f3a6c31484918a482. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### IQL Average Score: 42.3. Result ID: 6993cd6f3a6c31484918a488. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### IQL Average Score: 42.2. Result ID: 6993cd6f3a6c31484918a480. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### TRACER Average Score: 40. Result ID: 6993cd6f3a6c31484918a48a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### EDAC Average Score: 38.6. Result ID: 6993cd6f3a6c31484918a484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### IQL Average Score: 36.7. Result ID: 6993cd6f3a6c31484918a490. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### BC Average Score: 35.8. Result ID: 6993cd6f3a6c31484918a47b. [Reporting paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### BC Average Score: 35.8. Result ID: 6993cd6f3a6c31484918a483. [Reporting paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### BC Average Score: 35.8. Result ID: 6993cd6f3a6c31484918a48b. [Reporting paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### UWMSG Average Score: 35.6. Result ID: 6993cd6f3a6c31484918a486. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### TRACER Average Score: 34.2. Result ID: 6993cd6f3a6c31484918a47a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### BC Average Score: 33.4. Result ID: 6993cd6f3a6c31484918a473. [Reporting paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### CQL Average Score: 32.6. Result ID: 6993cd6f3a6c31484918a487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### CQL Average Score: 29.2. Result ID: 6993cd6f3a6c31484918a48f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### RIQL Average Score: 27.3. Result ID: 6993cd6f3a6c31484918a479. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### IQL Average Score: 21.4. Result ID: 6993cd6f3a6c31484918a478. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### CQL Average Score: 19.9. Result ID: 6993cd6f3a6c31484918a47f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"action"}. This record does not assert independent reproduction. ### MSG Average Score: 17.5. Result ID: 6993cd6f3a6c31484918a485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"reward"}. This record does not assert independent reproduction. ### CQL Average Score: 9. Result ID: 6993cd6f3a6c31484918a477. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### UWMSG Average Score: 2.9. Result ID: 6993cd6f3a6c31484918a476. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### UWMSG Average Score: 2.9. Result ID: 6993cd6f3a6c31484918a48e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### EDAC Average Score: 2.1. Result ID: 6993cd6f3a6c31484918a474. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. ### MSG Average Score: 1.7. Result ID: 6993cd6f3a6c31484918a48d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### EDAC Average Score: 1.5. Result ID: 6993cd6f3a6c31484918a48c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"dynamics"}. This record does not assert independent reproduction. ### MSG Average Score: -0.2. Result ID: 6993cd6f3a6c31484918a475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Corrupted Element":"observation"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.