# Offline Reinforcement Learning on Antmaze large-play v2 Source: [Offline Reinforcement Learning on Antmaze large-play v2]() Collection index: [llms.txt]() Data updated: 2026-05-26T07:38:06.030Z Evaluation of Offline Reinforcement Learning performance specifically on the AntMaze large-play environment using the v2 configuration, reporting the D4RL 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) | Antmaze large-play v2 | | Metric | D4RL Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [D4RL Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | D4RL Score | Result date | Report paper | | --- | --- | --- | --- | | Inverter | 0.93 | Not recorded | 6a1528e1dbd7150506f7dc83 | | ReBRAC | 0.522 | Not recorded | 6a1528e1dbd7150506f7dc83 | | IQL | 0.42 | Not recorded | 6a1528e1dbd7150506f7dc83 | | CQL | 0.208 | Not recorded | 6a1528e1dbd7150506f7dc83 | | BC | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | BC-10% | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | TD3+BC | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | AWAC | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | SAC-N | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | EDAC | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | | DT | 0 | Not recorded | 6a1528e1dbd7150506f7dc83 | ### Inverter D4RL Score: 0.93. Result ID: 6a154db5fbc373592c0c5c2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"1.0x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### ReBRAC D4RL Score: 0.522. Result ID: 6a154db5fbc373592c0c5c29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"1.6x†","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"JAX+JIT"}. This record does not assert independent reproduction. ### IQL D4RL Score: 0.42. Result ID: 6a154db5fbc373592c0c5c28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"12.6x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### CQL D4RL Score: 0.208. Result ID: 6a154db5fbc373592c0c5c27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"13.7x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### BC D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"x slower per env step":"12.7x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### BC-10% D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"9.3x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### TD3+BC D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"x slower per env step":"12.5x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### AWAC D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"9.6x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### SAC-N D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"13.4x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### EDAC D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"13.0x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. ### DT D4RL Score: 0. Result ID: 6a154db5fbc373592c0c5c2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"x slower per env step":"26.6x","Hardware":"single A40 GPU","Batch size":"1","Number of episodes":"100","Implementation framework":"PyTorch"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.