# Offline Reinforcement Learning on D4RL HalfCheetah-Full-Replay Source: [Offline Reinforcement Learning on D4RL HalfCheetah-Full-Replay]() Collection index: [llms.txt]() Data updated: 2026-05-11T09:09:25.491Z Evaluation of Offline Reinforcement Learning performance on the D4RL HalfCheetah environment using the Full-Replay dataset configuration, measured by Normalized 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) | D4RL HalfCheetah-Full-Replay | | Metric | Normalized Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Normalized Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Normalized Score | Result date | Report paper | | --- | --- | --- | --- | | PSPO | 94.9 | Not recorded | 6a016269dbc836b87d822f97 | | PMDB | 90 | Not recorded | 69b0f7262d603e6de3e45ee5 | | PMDB | 90 | Not recorded | 6a016269dbc836b87d822f97 | | RAMBO | 87 | Not recorded | 69b0f7262d603e6de3e45ee5 | | RAMBO | 87 | Not recorded | 6a016269dbc836b87d822f97 | | AMG | 86.3 | Not recorded | 69b0f7262d603e6de3e45ee5 | | ADM | 86.3 | Not recorded | 6a016269dbc836b87d822f97 | | EPQ | 85.3 | Not recorded | 69b0f7262d603e6de3e45ee5 | | EPQ | 85.3 | Not recorded | 6a016269dbc836b87d822f97 | | RRPI | 83.7 | Not recorded | 69b0f7262d603e6de3e45ee5 | | DMG | 79.9 | Not recorded | 69b0f7262d603e6de3e45ee5 | | DMG | 79.9 | Not recorded | 6a016269dbc836b87d822f97 | | CQL | 76.9 | Not recorded | 69b0f7262d603e6de3e45ee5 | | CQL | 76.9 | Not recorded | 6a016269dbc836b87d822f97 | | MOReL | 70.1 | Not recorded | 69b0f7262d603e6de3e45ee5 | | MOReL | 70.1 | Not recorded | 6a016269dbc836b87d822f97 | ### PSPO Normalized Score: 94.9. Result ID: 6a019caf47f34ce924e3b011. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Averaged across":"4 random seeds"}. This record does not assert independent reproduction. ### PMDB Normalized Score: 90. Result ID: 69b128c56dbb7075b95b930e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### PMDB Normalized Score: 90. Result ID: 6a019caf47f34ce924e3b00f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RAMBO Normalized Score: 87. Result ID: 69b128c56dbb7075b95b930d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### RAMBO Normalized Score: 87. Result ID: 6a019caf47f34ce924e3b00e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AMG Normalized Score: 86.3. Result ID: 69b128c56dbb7075b95b930f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### ADM Normalized Score: 86.3. Result ID: 6a019caf47f34ce924e3b010. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EPQ Normalized Score: 85.3. Result ID: 69b128c56dbb7075b95b930b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### EPQ Normalized Score: 85.3. Result ID: 6a019caf47f34ce924e3b00c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RRPI Normalized Score: 83.7. Result ID: 69b128c56dbb7075b95b9310. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### DMG Normalized Score: 79.9. Result ID: 69b128c56dbb7075b95b930a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### DMG Normalized Score: 79.9. Result ID: 6a019caf47f34ce924e3b00b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CQL Normalized Score: 76.9. Result ID: 69b128c56dbb7075b95b9309. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### CQL Normalized Score: 76.9. Result ID: 6a019caf47f34ce924e3b00a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MOReL Normalized Score: 70.1. Result ID: 69b128c56dbb7075b95b930c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of random seeds":"4"}. This record does not assert independent reproduction. ### MOReL Normalized Score: 70.1. Result ID: 6a019caf47f34ce924e3b00d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.