# Navigation on FrozenLake Source: [Navigation on FrozenLake]() Collection index: [llms.txt]() Data updated: 2026-05-15T08:43:13.622Z Evaluation of agent navigation performance on the standard FrozenLake environment, reporting the success rate. 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 | Navigation | | Dataset (including any stated split) | FrozenLake | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | ActFocus | 27 | Not recorded | 6a06a87cdbc836b87d829f88 | | ActFocus | 27 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 26.2 | Not recorded | 6a06a87cdbc836b87d829f88 | | ActFocus | 25.2 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 24.6 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 23.8 | Not recorded | 6a06a87cdbc836b87d829f88 | | ActFocus | 20.9 | Not recorded | 6a06a87cdbc836b87d829f88 | | ActFocus | 19.1 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 16.6 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 16.2 | Not recorded | 6a06a87cdbc836b87d829f88 | | ActFocus | 15.6 | Not recorded | 6a06a87cdbc836b87d829f88 | | Uniform | 5.1 | Not recorded | 6a06a87cdbc836b87d829f88 | ### ActFocus Success Rate: 27. Result ID: 6a06dc9247f34ce924ee90f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"3B","Evaluation Step":"200"}. This record does not assert independent reproduction. ### ActFocus Success Rate: 27. Result ID: 6a06dc9247f34ce924ee9106. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"PPO","Model Scale":"3B"}. This record does not assert independent reproduction. ### Uniform Success Rate: 26.2. Result ID: 6a06dc9247f34ce924ee9107. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"GRPO","Model Scale":"3B"}. This record does not assert independent reproduction. ### ActFocus Success Rate: 25.2. Result ID: 6a06dc9247f34ce924ee910c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"GRPO","Model Scale":"0.5B"}. This record does not assert independent reproduction. ### Uniform Success Rate: 24.6. Result ID: 6a06dc9247f34ce924ee9105. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"PPO","Model Scale":"3B"}. This record does not assert independent reproduction. ### Uniform Success Rate: 23.8. Result ID: 6a06dc9247f34ce924ee910b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"GRPO","Model Scale":"0.5B"}. This record does not assert independent reproduction. ### ActFocus Success Rate: 20.9. Result ID: 6a06dc9247f34ce924ee910a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"PPO","Model Scale":"0.5B"}. This record does not assert independent reproduction. ### ActFocus Success Rate: 19.1. Result ID: 6a06dc9247f34ce924ee9108. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"GRPO","Model Scale":"3B"}. This record does not assert independent reproduction. ### Uniform Success Rate: 16.6. Result ID: 6a06dc9247f34ce924ee90f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"3B","Evaluation Step":"200"}. This record does not assert independent reproduction. ### Uniform Success Rate: 16.2. Result ID: 6a06dc9247f34ce924ee9109. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Algorithm":"PPO","Model Scale":"0.5B"}. This record does not assert independent reproduction. ### ActFocus Success Rate: 15.6. Result ID: 6a06dc9247f34ce924ee90f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"0.5B","Evaluation Step":"200"}. This record does not assert independent reproduction. ### Uniform Success Rate: 5.1. Result ID: 6a06dc9247f34ce924ee90f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"0.5B","Evaluation Step":"200"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.