# Offline Reinforcement Learning on D4RL Gym-MuJoCo walker2d-expert Source: [Offline Reinforcement Learning on D4RL Gym-MuJoCo walker2d-expert]() Collection index: [llms.txt]() Data updated: 2026-06-15T07:24:02.892Z Evaluation of Offline Reinforcement Learning performance on the D4RL Walker2D environment using the MuJoCo physics engine, specifically using the 'expert' dataset configuration. 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-MuJoCo walker2d-expert | | Metric | Normalized Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 | | --- | --- | --- | --- | | DMG | 114.7 | Not recorded | 6a02b3ebdbc836b87d824520 | | DOSER | 111.2 | Not recorded | 6a02b3ebdbc836b87d824520 | | OneStep | 110.7 | Not recorded | 6a02b3ebdbc836b87d824520 | | TD3+BC | 110.2 | Not recorded | 6a02b3ebdbc836b87d824520 | | AWAC | 110.1 | Not recorded | 6a02b3ebdbc836b87d824520 | | TD3+BC | 110.1 | Not recorded | 6a2f86e2d33dfb23e783be29 | | IQL | 109.9 | Not recorded | 6a02b3ebdbc836b87d824520 | | IQL | 109.6 | Not recorded | 6a2f86e2d33dfb23e783be29 | | DT | 108.9 | Not recorded | 6a2f86e2d33dfb23e783be29 | | PDiT | 108.8 | Not recorded | 6a2f86e2d33dfb23e783be29 | | BC | 108.7 | Not recorded | 6a2f86e2d33dfb23e783be29 | | DRIVE | 108.6 | Not recorded | 6a2f86e2d33dfb23e783be29 | | CQL | 108.5 | Not recorded | 6a02b3ebdbc836b87d824520 | | DT | 108.3 | Not recorded | 6a02b3ebdbc836b87d824520 | | BC | 107.7 | Not recorded | 6a02b3ebdbc836b87d824520 | | BEAR | 106.6 | Not recorded | 6a02b3ebdbc836b87d824520 | | BCQ | 106.3 | Not recorded | 6a02b3ebdbc836b87d824520 | | CQL | 98.7 | Not recorded | 6a2f86e2d33dfb23e783be29 | | BEAR | 40.1 | Not recorded | 6a2f86e2d33dfb23e783be29 | ### DMG Normalized Score: 114.7. Result ID: 6a02d46147f34ce924e53143. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DOSER Normalized Score: 111.2. Result ID: 6a02d46147f34ce924e53144. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OneStep Normalized Score: 110.7. Result ID: 6a02d46147f34ce924e5313f. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TD3+BC Normalized Score: 110.2. Result ID: 6a02d46147f34ce924e53140. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AWAC Normalized Score: 110.1. Result ID: 6a02d46147f34ce924e5313e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TD3+BC Normalized Score: 110.1. Result ID: 6a2fa879fbc373592c2b921f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### IQL Normalized Score: 109.9. Result ID: 6a02d46147f34ce924e53142. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IQL Normalized Score: 109.6. Result ID: 6a2fa879fbc373592c2b921d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### DT Normalized Score: 108.9. Result ID: 6a2fa879fbc373592c2b9221. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### PDiT Normalized Score: 108.8. Result ID: 6a2fa879fbc373592c2b9222. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### BC Normalized Score: 108.7. Result ID: 6a2fa879fbc373592c2b9220. [Reporting paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### DRIVE Normalized Score: 108.6. Result ID: 6a2fa879fbc373592c2b9223. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### CQL Normalized Score: 108.5. Result ID: 6a02d46147f34ce924e53141. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DT Normalized Score: 108.3. Result ID: 6a02d46147f34ce924e5313d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BC Normalized Score: 107.7. Result ID: 6a02d46147f34ce924e5313a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BEAR Normalized Score: 106.6. Result ID: 6a02d46147f34ce924e5313c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BCQ Normalized Score: 106.3. Result ID: 6a02d46147f34ce924e5313b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CQL Normalized Score: 98.7. Result ID: 6a2fa879fbc373592c2b921c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. ### BEAR Normalized Score: 40.1. Result ID: 6a2fa879fbc373592c2b921e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Seeds":"5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.