# Offline Reinforcement Learning on D4RL Adroit relocate v0 (cloned) Source: [Offline Reinforcement Learning on D4RL Adroit relocate v0 (cloned)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:55.159Z Evaluation of Offline Reinforcement Learning performance specifically on the D4RL Adroit 'relocate' environment configuration using the cloned v0 dataset. 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 Adroit relocate v0 (cloned) | | Metric | Normalized Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 24 of 24 | | 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. - [Normalized Return](): Higher is better; unit: SCALAR. ## Recorded results | Method | Normalized Score | Result date | Report paper | | --- | --- | --- | --- | | ReBRAC | 0.9 | Not recorded | 699bdedb09c33900fcd80332 | | FAC | 0.5 | Not recorded | 699bdedb09c33900fcd80332 | | Easy BCQ | 0.3 | Not recorded | 68fa6b631e209131cea2df51 | | IQL | 0.2 | Not recorded | 699bdedb09c33900fcd80332 | | Rev. KL Reg. | 0.1 | Not recorded | 68fa6b631e209131cea2df51 | | Exp. Weight | 0.1 | Not recorded | 68fa6b631e209131cea2df51 | | EPQ | 0.1 | Not recorded | 699bdedb09c33900fcd80332 | | BC | 0 | Not recorded | 68fa6b631e209131cea2df51 | | MCQ | 0 | Not recorded | 699bdedb09c33900fcd80332 | | SAC-RND | 0 | Not recorded | 699bdedb09c33900fcd80332 | | IDQL | 0 | Not recorded | 699bdedb09c33900fcd80332 | | SRPO | 0 | Not recorded | 699bdedb09c33900fcd80332 | | CAC | 0 | Not recorded | 699bdedb09c33900fcd80332 | | FQL | 0 | Not recorded | 699bdedb09c33900fcd80332 | | Fu et al. | -0.1 | Not recorded | 68fa6b631e209131cea2df51 | | TD3+BC | -0.1 | Not recorded | 699bdedb09c33900fcd80332 | | CQL | -0.1 | Not recorded | 699bdedb09c33900fcd80332 | ### ReBRAC Normalized Score: 0.9. Result ID: 699d07635698665ec4a77573. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### FAC Normalized Score: 0.5. Result ID: 699d07635698665ec4a77578. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Flow","Seeds":8}. This record does not assert independent reproduction. ### Easy BCQ Normalized Score: 0.3. Result ID: 698e85bcffc3901de09e51ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction. ### IQL Normalized Score: 0.2. Result ID: 699d07635698665ec4a7756e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### Rev. KL Reg. Normalized Score: 0.1. Result ID: 698e85bcffc3901de09e51af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction. ### Exp. Weight Normalized Score: 0.1. Result ID: 698e85bcffc3901de09e51b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction. ### EPQ Normalized Score: 0.1. Result ID: 699d07635698665ec4a77571. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### BC Normalized Score: 0. Result ID: 698e85bcffc3901de09e51ad. [Reporting paper]() Recorded evaluation configuration: {"Algorithmic Template":"One-step"}. This record does not assert independent reproduction. ### MCQ Normalized Score: 0. Result ID: 699d07635698665ec4a77570. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### SAC-RND Normalized Score: 0. Result ID: 699d07635698665ec4a77572. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### IDQL Normalized Score: 0. Result ID: 699d07635698665ec4a77574. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Diffusion","Seeds":8}. This record does not assert independent reproduction. ### SRPO Normalized Score: 0. Result ID: 699d07635698665ec4a77575. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Diffusion","Seeds":8}. This record does not assert independent reproduction. ### CAC Normalized Score: 0. Result ID: 699d07635698665ec4a77576. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Diffusion","Seeds":8}. This record does not assert independent reproduction. ### FQL Normalized Score: 0. Result ID: 699d07635698665ec4a77577. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Flow","Seeds":8}. This record does not assert independent reproduction. ### Fu et al. Normalized Score: -0.1. Result ID: 698e85bcffc3901de09e51ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithmic Template":"Iterative"}. This record does not assert independent reproduction. ### TD3+BC Normalized Score: -0.1. Result ID: 699d07635698665ec4a7756d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. ### CQL Normalized Score: -0.1. Result ID: 699d07635698665ec4a7756f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Type":"Gaussian","Seeds":8}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.