# Offline Reinforcement Learning on Maze2D umaze v1 Source: [Offline Reinforcement Learning on Maze2D umaze v1]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:46.169Z Evaluation of Offline Reinforcement Learning performance on the Maze2D umaze environment, version 1, typically measured by normalized 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) | Maze2D umaze v1 | | Metric | Normalized Return | | 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 - [Normalized Return](): Higher is better; unit: SCALAR. ## Recorded results | Method | Normalized Return | Result date | Report paper | | --- | --- | --- | --- | | PrivORL-j | 52.2 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j | 49.9 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j | 49.8 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 49.3 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j | 45.5 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j | 42.1 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 41.2 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 39.8 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 38.8 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j | 38.7 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 32 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 28.9 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 28.4 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 28.2 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 26.8 | Not recorded | 6937ad596cfd488761a4eccc | | DP-Transformer | 25.9 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 24.6 | Not recorded | 6937ad596cfd488761a4eccc | | PrivORL-j-U | 11.2 | Not recorded | 6937ad596cfd488761a4eccc | ### PrivORL-j Normalized Return: 52.2. Result ID: 699706685698665ec45396b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j Normalized Return: 49.9. Result ID: 699706685698665ec45396c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j Normalized Return: 49.8. Result ID: 699706685698665ec45396bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"10"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 49.3. Result ID: 699706685698665ec45396c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j Normalized Return: 45.5. Result ID: 699706685698665ec45396b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"1"}. This record does not assert independent reproduction. ### PrivORL-j Normalized Return: 42.1. Result ID: 699706685698665ec45396bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"1"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 41.2. Result ID: 699706685698665ec45396ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"10"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 39.8. Result ID: 699706685698665ec45396b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 38.8. Result ID: 699706685698665ec45396be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j Normalized Return: 38.7. Result ID: 699706685698665ec45396c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"1"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 32. Result ID: 699706685698665ec45396b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"10"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 28.9. Result ID: 699706685698665ec45396b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"10"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 28.4. Result ID: 699706685698665ec45396b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"1"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 28.2. Result ID: 699706685698665ec45396bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"1"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 26.8. Result ID: 699706685698665ec45396bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"TD3PLUSBC","epsilon":"1"}. This record does not assert independent reproduction. ### DP-Transformer Normalized Return: 25.9. Result ID: 699706685698665ec45396b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"1"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 24.6. Result ID: 699706685698665ec45396b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"IQL","epsilon":"1"}. This record does not assert independent reproduction. ### PrivORL-j-U Normalized Return: 11.2. Result ID: 699706685698665ec45396b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RL Algorithm":"EDAC","epsilon":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.