# Point Robot Navigation on Point robot navigation tasks (meta-test)

Source: [Point Robot Navigation on Point robot navigation tasks (meta-test)](<https://www.sota2.com/research/sota/point-robot-navigation-on-point-robot-navigation-tasks-meta-test>)

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

Data updated: 2026-02-26T05:35:55.701Z

Evaluation of point robot navigation performance on the meta-test set of the Point robot navigation tasks environment, focusing on step-wise reward metrics and Conditional Value at Risk (CVaR).

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 | Point robot navigation |
| Dataset (including any stated split) | Point robot navigation tasks (meta-test) |
| Metric | Average Step-wise Reward |
| Unit | SCALAR |
| 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

- [Average Step-wise Reward](<https://www.sota2.com/research/sota/point-robot-navigation-on-point-robot-navigation-tasks-meta-test.md?metric=Average%20Step-wise%20Reward>): Higher is better; unit: SCALAR.

- [Worst Step-wise Reward](<https://www.sota2.com/research/sota/point-robot-navigation-on-point-robot-navigation-tasks-meta-test.md?metric=Worst%20Step-wise%20Reward>): Higher is better; unit: SCALAR.

- [CVaR (alpha)](<https://www.sota2.com/research/sota/point-robot-navigation-on-point-robot-navigation-tasks-meta-test.md?metric=CVaR%20(alpha)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Average Step-wise Reward | Result date | Report paper |
| --- | --- | --- | --- |
| DR-MAML | -15.3 | Not recorded | 68fa70b61e209131cea4cbd4 |
| CNP | -16.6 | Not recorded | 68fa70b61e209131cea4cbd4 |
| TR-CNP | -36.8 | Not recorded | 68fa70b61e209131cea4cbd4 |

### DR-MAML

Average Step-wise Reward: -15.3. Result ID: 699155353a6c3148490760cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Implementation](<https://github.com/lgcollins/tr-maml>)

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

### CNP

Average Step-wise Reward: -16.6. Result ID: 699155353a6c3148490760cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64841e209131cea050f9.md>)

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

### TR-CNP

Average Step-wise Reward: -36.8. Result ID: 699155353a6c3148490760cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Implementation](<https://github.com/lgcollins/tr-maml>)

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

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