# Meta Reinforcement Learning on 2-D point robot navigation (meta-test)

Source: [Meta Reinforcement Learning on 2-D point robot navigation (meta-test)](<https://www.sota2.com/research/sota/meta-reinforcement-learning-on-2-d-point-robot-navigation-meta-test>)

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

Data updated: 2026-02-26T05:35:39.809Z

Evaluation of Meta Reinforcement Learning performance on the meta-test split of the 2-D point robot navigation environment, focusing on Average Return 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 | Meta Reinforcement Learning |
| Dataset (including any stated split) | 2-D point robot navigation (meta-test) |
| Metric | Average Return |
| Unit | SCALAR |
| 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

- [Average Return](<https://www.sota2.com/research/sota/meta-reinforcement-learning-on-2-d-point-robot-navigation-meta-test.md?metric=Average%20Return>): Higher is better; unit: SCALAR.

- [CVaR Return](<https://www.sota2.com/research/sota/meta-reinforcement-learning-on-2-d-point-robot-navigation-meta-test.md?metric=CVaR%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Average Return | Result date | Report paper |
| --- | --- | --- | --- |
| DR-MAML+ | -19.2 | Not recorded | 68fa75781e209131cea682df |
| DR-MAML | -19.6 | Not recorded | 68fa75781e209131cea682df |
| DRO-MAML | -20.9 | Not recorded | 68fa75781e209131cea682df |
| MAML | -21.1 | Not recorded | 68fa75781e209131cea682df |

### DR-MAML+

Average Return: -19.2. Result ID: 6993b2a33a6c31484917e941.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682df.md>)

[Implementation](<https://github.com/lvyiqin/DRMAML>)

Recorded evaluation configuration: {"Number of runs":4,"alpha (α)":0.5}. This record does not assert independent reproduction.

### DR-MAML

Average Return: -19.6. Result ID: 6993b2a33a6c31484917e940.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682df.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,"alpha (α)":0.5}. This record does not assert independent reproduction.

### DRO-MAML

Average Return: -20.9. Result ID: 6993b2a33a6c31484917e93f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682df.md>)

Recorded evaluation configuration: {"Number of runs":4,"alpha (α)":0.5}. This record does not assert independent reproduction.

### MAML

Average Return: -21.1. Result ID: 6993b2a33a6c31484917e93e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63861e209131ce9ff3e8.md>)

Recorded evaluation configuration: {"Number of runs":4,"alpha (α)":0.5}. This record does not assert independent reproduction.

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