# Dexterous Manipulation on D4RL Adroit Tasks Source: [Dexterous Manipulation on D4RL Adroit Tasks]() Collection index: [llms.txt]() Data updated: 2026-04-21T12:13:03.931Z Evaluation of dexterous manipulation policies on the D4RL Adroit benchmark, reporting performance metrics for individual tasks (Pen, Hammer, Door) compared against human and cloned expert baselines. 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 | Dexterous Manipulation | | Dataset (including any stated split) | D4RL Adroit Tasks | | Metric | Performance Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Performance Score](): Higher is better; unit: SCALAR. - [Pen Success Rate (Human)](): Higher is better; unit: PERCENT. - [Pen Success Rate (Cloned)](): Higher is better; unit: PERCENT. - [Hammer Performance Score (Human)](): Higher is better; unit: SCALAR. - [Hammer Performance Score (Cloned)](): Higher is better; unit: SCALAR. - [Door Performance Score (Human)](): Higher is better; unit: SCALAR. - [Door Performance Score (Cloned)](): Higher is better; unit: SCALAR. - [Average Performance Score](): Higher is better; unit: SCALAR. - [Performance Gain (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Performance Score | Result date | Report paper | | --- | --- | --- | --- | | ReBRAC | 59 | Not recorded | 69e704d37d0172140ec7efd4 | | IQL | 53 | Not recorded | 69e704d37d0172140ec7efd4 | | IDQL | 52 | Not recorded | 69e704d37d0172140ec7efd4 | | IFQL | 52 | Not recorded | 69e704d37d0172140ec7efd4 | | FQL | 52 | Not recorded | 69e704d37d0172140ec7efd4 | | SRPO | 51 | Not recorded | 69e704d37d0172140ec7efd4 | | FBRAC | 50 | Not recorded | 69e704d37d0172140ec7efd4 | | BC | 48 | Not recorded | 69e704d37d0172140ec7efd4 | | FAWAC | 48 | Not recorded | 69e704d37d0172140ec7efd4 | | FiDec | 46 | Not recorded | 69e704d37d0172140ec7efd4 | | CAC | 43 | Not recorded | 69e704d37d0172140ec7efd4 | | DeFlow | 34 | Not recorded | 69e704d37d0172140ec7efd4 | ### ReBRAC Performance Score: 59. Result ID: 69e769c347f34ce924ceefb3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Gaussian Policies","Seeds":"8"}. This record does not assert independent reproduction. ### IQL Performance Score: 53. Result ID: 69e769c347f34ce924ceefb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Gaussian Policies","Seeds":"8"}. This record does not assert independent reproduction. ### IDQL Performance Score: 52. Result ID: 69e769c347f34ce924ceefb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Diffusion Policies","Seeds":"8"}. This record does not assert independent reproduction. ### IFQL Performance Score: 52. Result ID: 69e769c347f34ce924ceefb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Flow Policies","Seeds":"8"}. This record does not assert independent reproduction. ### FQL Performance Score: 52. Result ID: 69e769c347f34ce924ceefba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Flow Policies","Seeds":"8"}. This record does not assert independent reproduction. ### SRPO Performance Score: 51. Result ID: 69e769c347f34ce924ceefb5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Diffusion Policies","Seeds":"8"}. This record does not assert independent reproduction. ### FBRAC Performance Score: 50. Result ID: 69e769c347f34ce924ceefb8. [Reporting paper]() Recorded evaluation configuration: {"Policy Category":"Diffusion Policies","Seeds":"8"}. This record does not assert independent reproduction. ### BC Performance Score: 48. Result ID: 69e769c347f34ce924ceefb1. [Reporting paper]() Recorded evaluation configuration: {"Policy Category":"Gaussian Policies","Seeds":"8"}. This record does not assert independent reproduction. ### FAWAC Performance Score: 48. Result ID: 69e769c347f34ce924ceefb7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Diffusion Policies","Seeds":"8"}. This record does not assert independent reproduction. ### FiDec Performance Score: 46. Result ID: 69e769c347f34ce924ceefbc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Flow Policies","Seeds":"8"}. This record does not assert independent reproduction. ### CAC Performance Score: 43. Result ID: 69e769c347f34ce924ceefb6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Diffusion Policies","Seeds":"8"}. This record does not assert independent reproduction. ### DeFlow Performance Score: 34. Result ID: 69e769c347f34ce924ceefbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Category":"Flow Policies","Seeds":"8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.