# Offline Reinforcement Learning on MuJoCo HalfCheetah Friction shift

Source: [Offline Reinforcement Learning on MuJoCo HalfCheetah Friction shift](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-mujoco-halfcheetah-friction-shift>)

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

Data updated: 2026-05-26T09:18:41.823Z

Evaluation of Offline Reinforcement Learning performance on the MuJoCo HalfCheetah environment configured with a friction shift perturbation, 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) | MuJoCo HalfCheetah Friction shift |
| Metric | Normalized Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 32 of 32 |
| 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-mujoco-halfcheetah-friction-shift.md?metric=Normalized%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Normalized Score | Result date | Report paper |
| --- | --- | --- | --- |
| CEDGE-Planner | 72.13 | Not recorded | 6a15290fdbd7150506f7de50 |
| Diffuser | 71.25 | Not recorded | 6a15290fdbd7150506f7de50 |
| IQL | 69.8 | Not recorded | 6a15290fdbd7150506f7de50 |
| MOBODY | 69.54 | Not recorded | 6a15290fdbd7150506f7de50 |
| BOSA | 68.93 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Policy | 68.56 | Not recorded | 6a15290fdbd7150506f7de50 |
| DARA | 64.89 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Policy | 64.31 | Not recorded | 6a15290fdbd7150506f7de50 |
| MOBODY | 59.2 | Not recorded | 6a15290fdbd7150506f7de50 |
| MOBODY | 57.53 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Policy | 52.06 | Not recorded | 6a15290fdbd7150506f7de50 |
| MOBODY | 50.02 | Not recorded | 6a15290fdbd7150506f7de50 |
| TD3-BC | 49.43 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Policy | 49.15 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Planner | 47.93 | Not recorded | 6a15290fdbd7150506f7de50 |
| Diffuser | 46.91 | Not recorded | 6a15290fdbd7150506f7de50 |
| BOSA | 46.53 | Not recorded | 6a15290fdbd7150506f7de50 |
| DARA | 46.25 | Not recorded | 6a15290fdbd7150506f7de50 |
| IQL | 46.04 | Not recorded | 6a15290fdbd7150506f7de50 |
| IQL | 44.96 | Not recorded | 6a15290fdbd7150506f7de50 |
| BOSA | 44.07 | Not recorded | 6a15290fdbd7150506f7de50 |
| TD3-BC | 43.51 | Not recorded | 6a15290fdbd7150506f7de50 |
| DARA | 40.06 | Not recorded | 6a15290fdbd7150506f7de50 |
| TD3-BC | 35.83 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Planner | 32.79 | Not recorded | 6a15290fdbd7150506f7de50 |
| Diffuser | 32.11 | Not recorded | 6a15290fdbd7150506f7de50 |
| IQL | 26.39 | Not recorded | 6a15290fdbd7150506f7de50 |
| DARA | 23.69 | Not recorded | 6a15290fdbd7150506f7de50 |
| BOSA | 12.53 | Not recorded | 6a15290fdbd7150506f7de50 |
| Diffuser | 10.7 | Not recorded | 6a15290fdbd7150506f7de50 |
| CEDGE-Planner | 10.55 | Not recorded | 6a15290fdbd7150506f7de50 |
| TD3-BC | 8.95 | Not recorded | 6a15290fdbd7150506f7de50 |

### CEDGE-Planner

Normalized Score: 72.13. Result ID: 6a156524fbc373592c0d14be.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### Diffuser

Normalized Score: 71.25. Result ID: 6a156524fbc373592c0d14bd.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 69.8. Result ID: 6a156524fbc373592c0d14b9.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### MOBODY

Normalized Score: 69.54. Result ID: 6a156524fbc373592c0d14bc.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c431e209131cea8d3db.md>)

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### BOSA

Normalized Score: 68.93. Result ID: 6a156524fbc373592c0d14b8.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe21e209131cea47ea2.md>)

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### CEDGE-Policy

Normalized Score: 68.56. Result ID: 6a156524fbc373592c0d14cf.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### DARA

Normalized Score: 64.89. Result ID: 6a156524fbc373592c0d14bb.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31907.md>)

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### CEDGE-Policy

Normalized Score: 64.31. Result ID: 6a156524fbc373592c0d14b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### MOBODY

Normalized Score: 59.2. Result ID: 6a156524fbc373592c0d14cc.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c431e209131cea8d3db.md>)

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### MOBODY

Normalized Score: 57.53. Result ID: 6a156524fbc373592c0d14b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c431e209131cea8d3db.md>)

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### CEDGE-Policy

Normalized Score: 52.06. Result ID: 6a156524fbc373592c0d14bf.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### MOBODY

Normalized Score: 50.02. Result ID: 6a156524fbc373592c0d14c4.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c431e209131cea8d3db.md>)

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### TD3-BC

Normalized Score: 49.43. Result ID: 6a156524fbc373592c0d14ba.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

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

Recorded evaluation configuration: {"Level":"0.5"}. This record does not assert independent reproduction.

### CEDGE-Policy

Normalized Score: 49.15. Result ID: 6a156524fbc373592c0d14c7.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### CEDGE-Planner

Normalized Score: 47.93. Result ID: 6a156524fbc373592c0d14c6.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### Diffuser

Normalized Score: 46.91. Result ID: 6a156524fbc373592c0d14c5.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### BOSA

Normalized Score: 46.53. Result ID: 6a156524fbc373592c0d14c0.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe21e209131cea47ea2.md>)

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### DARA

Normalized Score: 46.25. Result ID: 6a156524fbc373592c0d14c3.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31907.md>)

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 46.04. Result ID: 6a156524fbc373592c0d14c1.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 44.96. Result ID: 6a156524fbc373592c0d14c9.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### BOSA

Normalized Score: 44.07. Result ID: 6a156524fbc373592c0d14c8.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe21e209131cea47ea2.md>)

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### TD3-BC

Normalized Score: 43.51. Result ID: 6a156524fbc373592c0d14c2.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

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

Recorded evaluation configuration: {"Level":"2.0"}. This record does not assert independent reproduction.

### DARA

Normalized Score: 40.06. Result ID: 6a156524fbc373592c0d14cb.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31907.md>)

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### TD3-BC

Normalized Score: 35.83. Result ID: 6a156524fbc373592c0d14ca.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

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

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### CEDGE-Planner

Normalized Score: 32.79. Result ID: 6a156524fbc373592c0d14ce.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### Diffuser

Normalized Score: 32.11. Result ID: 6a156524fbc373592c0d14cd.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"5.0"}. This record does not assert independent reproduction.

### IQL

Normalized Score: 26.39. Result ID: 6a156524fbc373592c0d14b1.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### DARA

Normalized Score: 23.69. Result ID: 6a156524fbc373592c0d14b3.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31907.md>)

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### BOSA

Normalized Score: 12.53. Result ID: 6a156524fbc373592c0d14b0.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe21e209131cea47ea2.md>)

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### Diffuser

Normalized Score: 10.7. Result ID: 6a156524fbc373592c0d14b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### CEDGE-Planner

Normalized Score: 10.55. Result ID: 6a156524fbc373592c0d14b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

### TD3-BC

Normalized Score: 8.95. Result ID: 6a156524fbc373592c0d14b2.

[Reporting paper](<https://www.sota2.com/research/paper/6a15290fdbd7150506f7de50.md>)

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

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

Recorded evaluation configuration: {"Level":"0.1"}. This record does not assert independent reproduction.

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