# Offline Policy Evaluation on D4RL HalfCheetah medium-replay

Source: [Offline Policy Evaluation on D4RL HalfCheetah medium-replay](<https://www.sota2.com/research/sota/offline-policy-evaluation-on-d4rl-halfcheetah-medium-replay>)

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

Data updated: 2026-02-26T05:59:58.697Z

Evaluation of Offline Policy Evaluation methods on the D4RL HalfCheetah environment using the medium-replay dataset configuration, measured by RMSE.

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 Policy Evaluation |
| Dataset (including any stated split) | D4RL HalfCheetah medium-replay |
| Metric | RMSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [RMSE](<https://www.sota2.com/research/sota/offline-policy-evaluation-on-d4rl-halfcheetah-medium-replay.md?metric=RMSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | RMSE | Result date | Report paper |
| --- | --- | --- | --- |
| OPERA | 46 | Not recorded | 68fa75751e209131cea680ea |
| BestOPE | 65 | Not recorded | 68fa75751e209131cea680ea |
| DR | 119.5 | Not recorded | 68fa75751e209131cea680ea |
| BVFT | 140.2 | Not recorded | 68fa75751e209131cea680ea |
| AvgOPE | 218.6 | Not recorded | 68fa75751e209131cea680ea |
| Dual-DICE | 567.9 | Not recorded | 68fa75751e209131cea680ea |
| MB | 750.9 | Not recorded | 68fa75751e209131cea680ea |

### OPERA

RMSE: 46. Result ID: 6993ae213a6c31484917c82d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

Recorded evaluation configuration: {"Estimator Category":"Multi-OPE Estimator"}. This record does not assert independent reproduction.

### BestOPE

RMSE: 65. Result ID: 6993ae213a6c31484917c82e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

Recorded evaluation configuration: {"Estimator Category":"Multi-OPE Estimator"}. This record does not assert independent reproduction.

### DR

RMSE: 119.5. Result ID: 6993ae213a6c31484917c831.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627d1e209131ce9f9890.md>)

Recorded evaluation configuration: {"Estimator Category":"Single OPE Estimator"}. This record does not assert independent reproduction.

### BVFT

RMSE: 140.2. Result ID: 6993ae213a6c31484917c830.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea26619.md>)

Recorded evaluation configuration: {"Estimator Category":"Multi-OPE Estimator"}. This record does not assert independent reproduction.

### AvgOPE

RMSE: 218.6. Result ID: 6993ae213a6c31484917c82f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

Recorded evaluation configuration: {"Estimator Category":"Multi-OPE Estimator"}. This record does not assert independent reproduction.

### Dual-DICE

RMSE: 567.9. Result ID: 6993ae213a6c31484917c832.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa572a1e209131ce9a2d56.md>)

Recorded evaluation configuration: {"Estimator Category":"Single OPE Estimator"}. This record does not assert independent reproduction.

### MB

RMSE: 750.9. Result ID: 6993ae213a6c31484917c833.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75751e209131cea680ea.md>)

Recorded evaluation configuration: {"Estimator Category":"Single OPE Estimator"}. This record does not assert independent reproduction.

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