# Locomotion on D4RL Gym-MuJoCo walker2d-medium v2

Source: [Locomotion on D4RL Gym-MuJoCo walker2d-medium v2](<https://www.sota2.com/research/sota/locomotion-on-d4rl-gym-mujoco-walker2d-medium-v2>)

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

Data updated: 2026-05-19T10:12:20.960Z

Evaluation of agent locomotion performance in the D4RL Walker2d environment using the medium dataset configuration, version 2.

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 | Locomotion |
| Dataset (including any stated split) | D4RL Gym-MuJoCo walker2d-medium v2 |
| Metric | Normalized Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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/locomotion-on-d4rl-gym-mujoco-walker2d-medium-v2.md?metric=Normalized%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Normalized Score | Result date | Report paper |
| --- | --- | --- | --- |
| DyDiff | 86.5 | Not recorded | 68fa73861e209131cea5cf46 |
| SynthER | 85 | Not recorded | 68fa73861e209131cea5cf46 |
| DiffQL | 84.3 | Not recorded | 68fa73861e209131cea5cf46 |
| DyDiff | 84.3 | Not recorded | 68fa73861e209131cea5cf46 |
| TD3 + BC | 83.7 | Not recorded | 68fa71411e209131cea5029d |
| SynthER | 83.5 | Not recorded | 68fa73861e209131cea5cf46 |
| SynthER | 82.5 | Not recorded | 68fa73861e209131cea5cf46 |
| Onestep RL | 81.8 | Not recorded | 68fa71411e209131cea5029d |
| DyDiff | 79.5 | Not recorded | 68fa73861e209131cea5cf46 |
| CQL | 79.3 | Not recorded | 68fa73861e209131cea5cf46 |
| IQL | 78.3 | Not recorded | 68fa71411e209131cea5029d |
| TD3BC | 76.8 | Not recorded | 68fa73861e209131cea5cf46 |
| BC 10% | 75.3 | Not recorded | 68fa71411e209131cea5029d |
| BC | 75 | Not recorded | 68fa71411e209131cea5029d |
| WT (Ours) | 74.8 | Not recorded | 68fa71411e209131cea5029d |
| CQL | 72.5 | Not recorded | 68fa71411e209131cea5029d |
| RvS-R/G | 71.7 | Not recorded | 68fa71411e209131cea5029d |
| DT | 69.2 | Not recorded | 68fa71411e209131cea5029d |
| QDT | 67.1 | Not recorded | 68fa71411e209131cea5029d |

### DyDiff

Normalized Score: 86.5. Result ID: 6a0c3771fbc373592c02dfb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

Recorded evaluation configuration: {"Base Policy":"TD3BC"}. This record does not assert independent reproduction.

### SynthER

Normalized Score: 85. Result ID: 6a0c3771fbc373592c02dfb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecb2.md>)

Recorded evaluation configuration: {"Base Policy":"DiffQL"}. This record does not assert independent reproduction.

### DiffQL

Normalized Score: 84.3. Result ID: 6a0c3771fbc373592c02dfb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

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

Recorded evaluation configuration: {"Data Augmentation":"None"}. This record does not assert independent reproduction.

### DyDiff

Normalized Score: 84.3. Result ID: 6a0c3771fbc373592c02dfb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

Recorded evaluation configuration: {"Base Policy":"DiffQL"}. This record does not assert independent reproduction.

### TD3 + BC

Normalized Score: 83.7. Result ID: 6991c16e3a6c3148490a5fd3.

[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.

### SynthER

Normalized Score: 83.5. Result ID: 6a0c3771fbc373592c02dfb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecb2.md>)

Recorded evaluation configuration: {"Base Policy":"TD3BC"}. This record does not assert independent reproduction.

### SynthER

Normalized Score: 82.5. Result ID: 6a0c3771fbc373592c02dfb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecb2.md>)

Recorded evaluation configuration: {"Base Policy":"CQL"}. This record does not assert independent reproduction.

### Onestep RL

Normalized Score: 81.8. Result ID: 6991c16e3a6c3148490a5fd4.

[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.

### DyDiff

Normalized Score: 79.5. Result ID: 6a0c3771fbc373592c02dfb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

Recorded evaluation configuration: {"Base Policy":"CQL"}. This record does not assert independent reproduction.

### CQL

Normalized Score: 79.3. Result ID: 6a0c3771fbc373592c02dfb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

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

Recorded evaluation configuration: {"Data Augmentation":"None"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 78.3. Result ID: 6991c16e3a6c3148490a5fd6.

[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.

### TD3BC

Normalized Score: 76.8. Result ID: 6a0c3771fbc373592c02dfaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf46.md>)

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

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

Recorded evaluation configuration: {"Data Augmentation":"None"}. This record does not assert independent reproduction.

### BC 10%

Normalized Score: 75.3. Result ID: 6991c16e3a6c3148490a5fd7.

[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

Normalized Score: 75. Result ID: 6991c16e3a6c3148490a5fd8.

[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.

### WT (Ours)

Normalized Score: 74.8. Result ID: 6991c16e3a6c3148490a5fdc.

[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.

### CQL

Normalized Score: 72.5. Result ID: 6991c16e3a6c3148490a5fd5.

[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: 71.7. Result ID: 6991c16e3a6c3148490a5fd9.

[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: 69.2. Result ID: 6991c16e3a6c3148490a5fda.

[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.

### QDT

Normalized Score: 67.1. Result ID: 6991c16e3a6c3148490a5fdb.

[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.

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