# Navigation on AntMaze (v2 Play Configurations)

Source: [Navigation on AntMaze (v2 Play Configurations)](<https://www.sota2.com/research/sota/navigation-on-antmaze-v2-play-configurations>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-04T08:50:12.476Z

Evaluation of agent navigation performance across AntMaze large and medium play v2 environments, reporting average performance metrics.

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) | AntMaze |
| Metric | Success Rate (Large Play v2) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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 (Large Play v2)](<https://www.sota2.com/research/sota/navigation-on-antmaze-v2-play-configurations.md?metric=Success%20Rate%20(Large%20Play%20v2)>): Higher is better; unit: PERCENT.

- [Success Rate (Medium Play v2)](<https://www.sota2.com/research/sota/navigation-on-antmaze-v2-play-configurations.md?metric=Success%20Rate%20(Medium%20Play%20v2)>): Higher is better; unit: PERCENT.

- [Average Success Rate (AntMaze v2)](<https://www.sota2.com/research/sota/navigation-on-antmaze-v2-play-configurations.md?metric=Average%20Success%20Rate%20(AntMaze%20v2)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Success Rate (Large Play v2) | Result date | Report paper |
| --- | --- | --- | --- |
| PrefMoE | 44.8 | Not recorded | 69f82815c0f56ed843088ab1 |
| PrefMMT | 36.8 | Not recorded | 69f82815c0f56ed843088ab1 |
| RIME-offline | 10.4 | Not recorded | 69f82815c0f56ed843088ab1 |
| MR | 6.4 | Not recorded | 69f82815c0f56ed843088ab1 |

### PrefMoE

Success Rate (Large Play v2): 44.8. Result ID: 69f85da947f34ce924dc2fe4.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

Recorded evaluation configuration: {"K":"4"}. This record does not assert independent reproduction.

### PrefMMT

Success Rate (Large Play v2): 36.8. Result ID: 69f85da947f34ce924dc2fe3.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77581e209131cea728d5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RIME-offline

Success Rate (Large Play v2): 10.4. Result ID: 69f85da947f34ce924dc2fe2.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67da3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MR

Success Rate (Large Play v2): 6.4. Result ID: 69f85da947f34ce924dc2fe1.

[Reporting paper](<https://www.sota2.com/research/paper/69f82815c0f56ed843088ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26067.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.