# Robustness evaluation on MAZE Ant Corridor7x7 v1

Source: [Robustness evaluation on MAZE Ant Corridor7x7 v1](<https://www.sota2.com/research/sota/robustness-evaluation-on-maze-ant-corridor7x7-v1>)

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

Data updated: 2026-02-26T06:02:23.488Z

Evaluation of system robustness performance on the MAZE Ant Corridor7x7 environment, version v1, reporting success percentage (Robustness %) and relative 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 | Robustness evaluation |
| Dataset (including any stated split) | MAZE Ant Corridor7x7 v1 (Robustness evaluation) |
| Metric | Robustness (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Robustness (%)](<https://www.sota2.com/research/sota/robustness-evaluation-on-maze-ant-corridor7x7-v1.md?metric=Robustness%20(%25)>): Higher is better; unit: PERCENT.

- [Relative to BC](<https://www.sota2.com/research/sota/robustness-evaluation-on-maze-ant-corridor7x7-v1.md?metric=Relative%20to%20BC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Robustness (%) | Result date | Report paper |
| --- | --- | --- | --- |
| BC | 21.7 | Not recorded | 68fa6da81e209131cea3b351 |
| VINS | 19.6 | Not recorded | 68fa6da81e209131cea3b351 |
| BMIL | 17.6 | Not recorded | 68fa6da81e209131cea3b351 |

### BC

Robustness (%): 21.7. Result ID: 698fb5663a6c314849fb4994.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b351.md>)

Recorded evaluation configuration: {"Agent type":"Ant","Number of demonstrations":"20","Number of trials":"100"}. This record does not assert independent reproduction.

### VINS

Robustness (%): 19.6. Result ID: 698fb5663a6c314849fb4995.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b351.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66801e209131cea10b25.md>)

Recorded evaluation configuration: {"Agent type":"Ant","Number of demonstrations":"20","Number of trials":"100"}. This record does not assert independent reproduction.

### BMIL

Robustness (%): 17.6. Result ID: 698fb5663a6c314849fb4996.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b351.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b351.md>)

[Implementation](<https://github.com/jypark0/bmil>)

Recorded evaluation configuration: {"Agent type":"Ant","Number of demonstrations":"20","Number of trials":"100"}. This record does not assert independent reproduction.

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