# Navigation on D4RL antmaze-umaze v2

Source: [Navigation on D4RL antmaze-umaze v2](<https://www.sota2.com/research/sota/navigation-on-d4rl-antmaze-umaze-v2>)

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

Data updated: 2026-02-26T05:53:50.720Z

Evaluation of agent navigation performance in the D4RL AntMaze U-Maze v2 environment using the Normalized Score metric.

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) | D4RL antmaze-umaze v2 |
| Metric | Normalized Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Normalized Score](<https://www.sota2.com/research/sota/navigation-on-d4rl-antmaze-umaze-v2.md?metric=Normalized%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Normalized Score | Result date | Report paper |
| --- | --- | --- | --- |
| IQL | 87.5 | Not recorded | 68fa71411e209131cea5029d |
| TD3 + BC | 78.6 | Not recorded | 68fa71411e209131cea5029d |
| CQL | 74 | Not recorded | 68fa71411e209131cea5029d |
| RvS-R/G | 65.4 | Not recorded | 68fa71411e209131cea5029d |
| QDT | 64.9 | Not recorded | 68fa71411e209131cea5029d |
| Onestep RL | 64.3 | Not recorded | 68fa71411e209131cea5029d |
| WT (Ours) | 64.1 | Not recorded | 68fa71411e209131cea5029d |
| BC | 62.8 | Not recorded | 68fa71411e209131cea5029d |
| BC 10% | 54.6 | Not recorded | 68fa71411e209131cea5029d |
| DT | 53.6 | Not recorded | 68fa71411e209131cea5029d |

### IQL

Normalized Score: 87.5. Result ID: 6991c16e3a6c3148490a5fe0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b67f.md>)

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

### TD3 + BC

Normalized Score: 78.6. Result ID: 6991c16e3a6c3148490a5fdd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df4f.md>)

[Implementation](<https://github.com/sfujim/TD3_BC>)

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

### CQL

Normalized Score: 74. Result ID: 6991c16e3a6c3148490a5fdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

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

### RvS-R/G

Normalized Score: 65.4. Result ID: 6991c16e3a6c3148490a5fe3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea3485c.md>)

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

### QDT

Normalized Score: 64.9. Result ID: 6991c16e3a6c3148490a5fe5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7b1e209131cea45dbf.md>)

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

### Onestep RL

Normalized Score: 64.3. Result ID: 6991c16e3a6c3148490a5fde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b631e209131cea2df51.md>)

[Implementation](<https://github.com/davidbrandfonbrener/onestep-rl>)

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

### WT (Ours)

Normalized Score: 64.1. Result ID: 6991c16e3a6c3148490a5fe6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Implementation](<https://github.com/sfujim/TD3_BC>)

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

### BC

Normalized Score: 62.8. Result ID: 6991c16e3a6c3148490a5fe2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea3485c.md>)

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

### BC 10%

Normalized Score: 54.6. Result ID: 6991c16e3a6c3148490a5fe1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c881e209131cea3485c.md>)

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

### DT

Normalized Score: 53.6. Result ID: 6991c16e3a6c3148490a5fe4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71411e209131cea5029d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a381e209131cea26b46.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.