# Offline Reinforcement Learning on D4RL Gym walker2d (full-replay) Source: [Offline Reinforcement Learning on D4RL Gym walker2d (full-replay)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:45.712Z Evaluation of Offline Reinforcement Learning performance using the D4RL Walker2D environment configured with the full replay dataset, typically measured by normalized average return. 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 Gym walker2d (full-replay) | | Metric | Normalized Return | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 Return](): Higher is better; unit: PERCENT. ## Recorded results | Method | Normalized Return | Result date | Report paper | | --- | --- | --- | --- | | BCQ | 108.4 | Not recorded | 68fa6aec1e209131cea2b133 | | SPQR | 102.2 | Not recorded | 68fa71b41e209131cea52a13 | | SPQR | 101.1 | Not recorded | 68fa71b41e209131cea52a13 | | EDAC | 99.8 | Not recorded | 68fa6aec1e209131cea2b133 | | EDAC | 99.8 | Not recorded | 68fa71b41e209131cea52a13 | | CQL-Min | 98.96 | Not recorded | 68fa71b41e209131cea52a13 | | MOREL | 96.9 | Not recorded | 68fa6aec1e209131cea2b133 | | SAC-N | 94.6 | Not recorded | 68fa6aec1e209131cea2b133 | | SAC-Min | 94.6 | Not recorded | 68fa71b41e209131cea52a13 | | CQL | 94.2 | Not recorded | 68fa6aec1e209131cea2b133 | | BRAC | 71 | Not recorded | 68fa6aec1e209131cea2b133 | | BC | 68.8 | Not recorded | 68fa6aec1e209131cea2b133 | | BC | 68.8 | Not recorded | 68fa71b41e209131cea52a13 | | UWAC | 60.7 | Not recorded | 68fa6aec1e209131cea2b133 | | SAC | 27.9 | Not recorded | 68fa6aec1e209131cea2b133 | | BEAR | 18.9 | Not recorded | 68fa6aec1e209131cea2b133 | | REM | 1.3 | Not recorded | 68fa6aec1e209131cea2b133 | ### BCQ Normalized Return: 108.4. Result ID: 698e41bbffc3901de09c12f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### SPQR Normalized Return: 102.2. Result ID: 6991dcb93a6c3148490b0f7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base algorithm":"EDAC"}. This record does not assert independent reproduction. ### SPQR Normalized Return: 101.1. Result ID: 6991dcb93a6c3148490b0f7a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base algorithm":"SAC-Min"}. This record does not assert independent reproduction. ### EDAC Normalized Return: 99.8. Result ID: 698e41bbffc3901de09c12f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Ours"}. This record does not assert independent reproduction. ### EDAC Normalized Return: 99.8. Result ID: 6991dcb93a6c3148490b0f78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CQL-Min Normalized Return: 98.96. Result ID: 6991dcb93a6c3148490b0f77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MOREL Normalized Return: 96.9. Result ID: 698e41bbffc3901de09c12f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### SAC-N Normalized Return: 94.6. Result ID: 698e41bbffc3901de09c12f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Ours"}. This record does not assert independent reproduction. ### SAC-Min Normalized Return: 94.6. Result ID: 6991dcb93a6c3148490b0f79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CQL Normalized Return: 94.2. Result ID: 698e41bbffc3901de09c12f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### BRAC Normalized Return: 71. Result ID: 698e41bbffc3901de09c12f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### BC Normalized Return: 68.8. Result ID: 698e41bbffc3901de09c12ee. [Reporting paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### BC Normalized Return: 68.8. Result ID: 6991dcb93a6c3148490b0f76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UWAC Normalized Return: 60.7. Result ID: 698e41bbffc3901de09c12f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### SAC Normalized Return: 27.9. Result ID: 698e41bbffc3901de09c12ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### BEAR Normalized Return: 18.9. Result ID: 698e41bbffc3901de09c12f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. ### REM Normalized Return: 1.3. Result ID: 698e41bbffc3901de09c12f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Implementation":"Reproduced"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.