# Offline Reinforcement Learning on D4RL halfcheetah-random v2

Source: [Offline Reinforcement Learning on D4RL halfcheetah-random v2](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-halfcheetah-random-v2>)

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

Data updated: 2026-06-02T08:50:31.954Z

Evaluation of Offline Reinforcement Learning performance on the D4RL HalfCheetah environment using the 'random v2' dataset configuration, measured by Normalized Score.

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 | Offline Reinforcement Learning |
| Dataset (including any stated split) | D4RL halfcheetah-random v2 |
| Metric | Normalized Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 35 of 35 |
| 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/offline-reinforcement-learning-on-d4rl-halfcheetah-random-v2.md?metric=Normalized%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Normalized Score | Result date | Report paper |
| --- | --- | --- | --- |
| ADM | 45.4 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| RAMBO | 39.5 | Not recorded | 68fa6dc91e209131cea3c318 |
| RAMBO | 39.5 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| MOREL | 38.9 | Not recorded | 68fa6dc91e209131cea3c318 |
| MOReL | 38.9 | Not recorded | 68fa6dc91e209131cea3c318 |
| MOReL | 38.9 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| PMDB | 37.8 | Not recorded | 68fa6dc91e209131cea3c318 |
| PMDB | 37.8 | Not recorded | 68fa6dc91e209131cea3c318 |
| PMDB | 37.8 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| MOPO | 35.9 | Not recorded | 699d30ad6017c4460ffab662 |
| PhyB | 34.7 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| EPQ | 33 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| Uncertainty-Aware Rank-One MIMO Q Network | 31.5 | Not recorded | 699d30ad6017c4460ffab662 |
| CQL | 31.3 | Not recorded | 68fa6dc91e209131cea3c318 |
| CQL | 31.3 | Not recorded | 68fa6dc91e209131cea3c318 |
| CQL | 31.3 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| DMG | 28.8 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| EDAC | 28.4 | Not recorded | 68fa6dc91e209131cea3c318 |
| EDAC | 28.4 | Not recorded | 68fa6dc91e209131cea3c318 |
| BRAC | 24.3 | Not recorded | 68fa6dc91e209131cea3c318 |
| BRAC | 24.3 | Not recorded | 68fa6dc91e209131cea3c318 |
| CQL | 17.5 | Not recorded | 699d30ad6017c4460ffab662 |
| IQL | 14.4 | Not recorded | 699d30ad6017c4460ffab662 |
| FQL | 14.2 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| EDAC-10 | 13.4 | Not recorded | 699d30ad6017c4460ffab662 |
| BEAR | 12.6 | Not recorded | 68fa6dc91e209131cea3c318 |
| BEAR | 12.6 | Not recorded | 68fa6dc91e209131cea3c318 |
| TD3-BC | 11 | Not recorded | 699d30ad6017c4460ffab662 |
| PBRL | 11 | Not recorded | 699d30ad6017c4460ffab662 |
| TD3+BC | 10.2 | Not recorded | 6a1e63c9dbd7150506f853f2 |
| BCQ | 2.3 | Not recorded | 699d30ad6017c4460ffab662 |
| BEAR | 2.3 | Not recorded | 699d30ad6017c4460ffab662 |
| UWAV | 2.3 | Not recorded | 699d30ad6017c4460ffab662 |
| BC | 2.2 | Not recorded | 68fa6dc91e209131cea3c318 |
| BC | 2.2 | Not recorded | 68fa6dc91e209131cea3c318 |

### ADM

Normalized Score: 45.4. Result ID: 6a1e9948fbc373592c18da45.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734e1e209131cea5baff.md>)

Recorded evaluation configuration: {"Model category":"Model-based"}. This record does not assert independent reproduction.

### RAMBO

Normalized Score: 39.5. Result ID: 698fea1b3a6c314849fcc0cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da51e209131cea3b264.md>)

[Implementation](<https://www.sota2.com/github.com/marc-rigter/rambo>)

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

### RAMBO

Normalized Score: 39.5. Result ID: 6a1e9948fbc373592c18da43.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da51e209131cea3b264.md>)

[Implementation](<https://www.sota2.com/github.com/marc-rigter/rambo>)

Recorded evaluation configuration: {"Model category":"Model-based"}. This record does not assert independent reproduction.

### MOREL

Normalized Score: 38.9. Result ID: 698fea1b3a6c314849fcc0cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

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

### MOReL

Normalized Score: 38.9. Result ID: 698fea1b3a6c314849fcc13b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

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

### MOReL

Normalized Score: 38.9. Result ID: 6a1e9948fbc373592c18da42.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Model category":"Model-based"}. This record does not assert independent reproduction.

### PMDB

Normalized Score: 37.8. Result ID: 698fea1b3a6c314849fcc0d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Implementation](<https://github.com/huawei-noah/HEBO/tree/master/PMDB>)

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

### PMDB

Normalized Score: 37.8. Result ID: 698fea1b3a6c314849fcc13d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Implementation](<https://github.com/huawei-noah/HEBO/tree/master/PMDB>)

Recorded evaluation configuration: {"N":10,"k":2}. This record does not assert independent reproduction.

### PMDB

Normalized Score: 37.8. Result ID: 6a1e9948fbc373592c18da44.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Implementation](<https://github.com/huawei-noah/HEBO/tree/master/PMDB>)

Recorded evaluation configuration: {"Model category":"Model-based"}. This record does not assert independent reproduction.

### MOPO

Normalized Score: 35.9. Result ID: 699e58bc5698665ec4195309.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e111.md>)

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

### PhyB

Normalized Score: 34.7. Result ID: 6a1e9948fbc373592c18da46.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

Recorded evaluation configuration: {"Model category":"Model-based"}. This record does not assert independent reproduction.

### EPQ

Normalized Score: 33. Result ID: 6a1e9948fbc373592c18da3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74dd1e209131cea64466.md>)

Recorded evaluation configuration: {"Model category":"Model-free"}. This record does not assert independent reproduction.

### Uncertainty-Aware Rank-One MIMO Q Network

Normalized Score: 31.5. Result ID: 699e58bc5698665ec419530d.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

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

### CQL

Normalized Score: 31.3. Result ID: 698fea1b3a6c314849fcc0cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

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

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

### CQL

Normalized Score: 31.3. Result ID: 698fea1b3a6c314849fcc13a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

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

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

### CQL

Normalized Score: 31.3. Result ID: 6a1e9948fbc373592c18da3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

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

Recorded evaluation configuration: {"Model category":"Model-free"}. This record does not assert independent reproduction.

### DMG

Normalized Score: 28.8. Result ID: 6a1e9948fbc373592c18da41.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea692b2.md>)

[Implementation](<https://github.com/maoyixiu/DMG>)

Recorded evaluation configuration: {"Model category":"Model-free"}. This record does not assert independent reproduction.

### EDAC

Normalized Score: 28.4. Result ID: 698fea1b3a6c314849fcc0ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

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

### EDAC

Normalized Score: 28.4. Result ID: 698fea1b3a6c314849fcc13c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

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

### BRAC

Normalized Score: 24.3. Result ID: 698fea1b3a6c314849fcc0cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66b81e209131cea12110.md>)

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

### BRAC

Normalized Score: 24.3. Result ID: 698fea1b3a6c314849fcc139.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66b81e209131cea12110.md>)

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

### CQL

Normalized Score: 17.5. Result ID: 699e58bc5698665ec4195308.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

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

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

### IQL

Normalized Score: 14.4. Result ID: 699e58bc5698665ec4195305.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

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

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

### FQL

Normalized Score: 14.2. Result ID: 6a1e9948fbc373592c18da3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

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

Recorded evaluation configuration: {"Model category":"Model-free"}. This record does not assert independent reproduction.

### EDAC-10

Normalized Score: 13.4. Result ID: 699e58bc5698665ec419530b.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aec1e209131cea2b133.md>)

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

### BEAR

Normalized Score: 12.6. Result ID: 698fea1b3a6c314849fcc0ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66b51e209131cea11fd5.md>)

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

### BEAR

Normalized Score: 12.6. Result ID: 698fea1b3a6c314849fcc138.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66b51e209131cea11fd5.md>)

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

### TD3-BC

Normalized Score: 11. Result ID: 699e58bc5698665ec419530a.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.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.

### PBRL

Normalized Score: 11. Result ID: 699e58bc5698665ec419530c.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6be01e209131cea30cd8.md>)

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

### TD3+BC

Normalized Score: 10.2. Result ID: 6a1e9948fbc373592c18da40.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e63c9dbd7150506f853f2.md>)

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

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

Recorded evaluation configuration: {"Model category":"Model-free"}. This record does not assert independent reproduction.

### BCQ

Normalized Score: 2.3. Result ID: 699e58bc5698665ec4195304.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

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

### BEAR

Normalized Score: 2.3. Result ID: 699e58bc5698665ec4195306.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66b51e209131cea11fd5.md>)

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

### UWAV

Normalized Score: 2.3. Result ID: 699e58bc5698665ec4195307.

[Reporting paper](<https://www.sota2.com/research/paper/699d30ad6017c4460ffab662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ef1e209131cea25058.md>)

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

### BC

Normalized Score: 2.2. Result ID: 698fea1b3a6c314849fcc0c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.md>)

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

### BC

Normalized Score: 2.2. Result ID: 698fea1b3a6c314849fcc137.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc91e209131cea3c318.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.
