# Navigation on D4RL antmaze-large-diverse (antmaze-l-d)

Source: [Navigation on D4RL antmaze-large-diverse (antmaze-l-d)](<https://www.sota2.com/research/sota/navigation-on-d4rl-antmaze-large-diverse-antmaze-l-d>)

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

Data updated: 2026-02-26T05:53:55.995Z

Evaluation of agent navigation performance in the D4RL AntMaze Large-Diverse 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-large-diverse (antmaze-l-d) |
| Metric | Normalized Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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-large-diverse-antmaze-l-d.md?metric=Normalized%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Normalized Score | Result date | Report paper |
| --- | --- | --- | --- |
| FQL | 83 | Not recorded | 68fa7bc01e209131cea8a30f |
| OFQL | 76.1 | Not recorded | 68fa7bc01e209131cea8a30f |
| POR | 73.4 | Not recorded | 68fa6eee1e209131cea42f64 |
| DQL | 56.6 | Not recorded | 68fa7bc01e209131cea8a30f |
| IQL | 47.5 | Not recorded | 68fa6eee1e209131cea42f64 |
| IQL | 47.5 | Not recorded | 68fa7bc01e209131cea8a30f |
| CQL | 45.6 | Not recorded | 68fa6eee1e209131cea42f64 |
| EDP | 41.3 | Not recorded | 68fa7bc01e209131cea8a30f |
| IDQL | 40 | Not recorded | 68fa7bc01e209131cea8a30f |
| RvS | 36.9 | Not recorded | 68fa6eee1e209131cea42f64 |
| Diffuser | 27.3 | Not recorded | 68fa7bc01e209131cea8a30f |
| 10%BC | 0 | Not recorded | 68fa6eee1e209131cea42f64 |
| One-step RL | 0 | Not recorded | 68fa6eee1e209131cea42f64 |
| DT | 0 | Not recorded | 68fa6eee1e209131cea42f64 |
| BC | 0 | Not recorded | 68fa7bc01e209131cea8a30f |
| TD3-BC | 0 | Not recorded | 68fa7bc01e209131cea8a30f |
| DD | 0 | Not recorded | 68fa7bc01e209131cea8a30f |

### FQL

Normalized Score: 83. Result ID: 699e9c6d5698665ec465ff01.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a67a.md>)

Recorded evaluation configuration: {"Category":"One-step Flow Policies"}. This record does not assert independent reproduction.

### OFQL

Normalized Score: 76.1. Result ID: 699e9c6d5698665ec465ff02.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

Recorded evaluation configuration: {"Category":"One-step Flow Policies"}. This record does not assert independent reproduction.

### POR

Normalized Score: 73.4. Result ID: 699071dc3a6c314849009ac8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

[Implementation](<https://github.com/ryanxhr/POR>)

Recorded evaluation configuration: {"Method Category":"Conditioned BC","Seeds":5}. This record does not assert independent reproduction.

### DQL

Normalized Score: 56.6. Result ID: 699e9c6d5698665ec465ff00.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70791e209131cea4b56e.md>)

Recorded evaluation configuration: {"Category":"Multi-step Diffusion Policies"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 47.5. Result ID: 699071dc3a6c314849009ac5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697b1e209131cea2254b.md>)

Recorded evaluation configuration: {"Method Category":"Weighted BC","Seeds":5}. This record does not assert independent reproduction.

### IQL

Normalized Score: 47.5. Result ID: 699e9c6d5698665ec465fefb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

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

Recorded evaluation configuration: {"Category":"Non-Diffusion Policies"}. This record does not assert independent reproduction.

### CQL

Normalized Score: 45.6. Result ID: 699071dc3a6c314849009ac9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

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

Recorded evaluation configuration: {"Method Category":"Best RL Baseline","Seeds":5}. This record does not assert independent reproduction.

### EDP

Normalized Score: 41.3. Result ID: 699e9c6d5698665ec465fefe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71071e209131cea4eb6d.md>)

Recorded evaluation configuration: {"Category":"Multi-step Diffusion Policies"}. This record does not assert independent reproduction.

### IDQL

Normalized Score: 40. Result ID: 699e9c6d5698665ec465feff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f731e209131cea45a93.md>)

Recorded evaluation configuration: {"Category":"Multi-step Diffusion Policies"}. This record does not assert independent reproduction.

### RvS

Normalized Score: 36.9. Result ID: 699071dc3a6c314849009ac7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

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

Recorded evaluation configuration: {"Method Category":"Conditioned BC","Seeds":5}. This record does not assert independent reproduction.

### Diffuser

Normalized Score: 27.3. Result ID: 699e9c6d5698665ec465fefc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e3b1e209131cea3e868.md>)

Recorded evaluation configuration: {"Category":"Diffusion Planners"}. This record does not assert independent reproduction.

### 10%BC

Normalized Score: 0. Result ID: 699071dc3a6c314849009ac3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

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

Recorded evaluation configuration: {"Method Category":"Weighted BC","Seeds":5}. This record does not assert independent reproduction.

### One-step RL

Normalized Score: 0. Result ID: 699071dc3a6c314849009ac4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

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

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

Recorded evaluation configuration: {"Method Category":"Weighted BC","Seeds":5}. This record does not assert independent reproduction.

### DT

Normalized Score: 0. Result ID: 699071dc3a6c314849009ac6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f64.md>)

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

Recorded evaluation configuration: {"Method Category":"Conditioned BC","Seeds":5}. This record does not assert independent reproduction.

### BC

Normalized Score: 0. Result ID: 699e9c6d5698665ec465fef9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

Recorded evaluation configuration: {"Category":"Non-Diffusion Policies"}. This record does not assert independent reproduction.

### TD3-BC

Normalized Score: 0. Result ID: 699e9c6d5698665ec465fefa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

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

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

Recorded evaluation configuration: {"Category":"Non-Diffusion Policies"}. This record does not assert independent reproduction.

### DD

Normalized Score: 0. Result ID: 699e9c6d5698665ec465fefd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a30f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ffa1e209131cea4849f.md>)

Recorded evaluation configuration: {"Category":"Diffusion Planners"}. This record does not assert independent reproduction.

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