# Offline Policy Evaluation on Sepsis-MDP (test)

Source: [Offline Policy Evaluation on Sepsis-MDP (test)](<https://www.sota2.com/research/sota/offline-policy-evaluation-on-sepsis-mdp-test>)

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

Data updated: 2026-02-26T05:50:48.994Z

Evaluation of Offline Policy Evaluation methods using the Sepsis-MDP dataset, specifically on the test split, reporting performance via MSE.

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) | Sepsis-MDP (test) |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [MSE](<https://www.sota2.com/research/sota/offline-policy-evaluation-on-sepsis-mdp-test.md?metric=MSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| OPERA | 0.1705 | Not recorded | 68fa75751e209131cea680ea |
| IS | 0.172 | Not recorded | 68fa75751e209131cea680ea |
| OPERA | 0.2205 | Not recorded | 68fa75751e209131cea680ea |
| FQE | 0.2448 | Not recorded | 68fa75751e209131cea680ea |
| IS | 0.2753 | Not recorded | 68fa75751e209131cea680ea |
| WIS | 0.2948 | Not recorded | 68fa75751e209131cea680ea |
| FQE | 0.2995 | Not recorded | 68fa75751e209131cea680ea |
| WIS | 0.2998 | Not recorded | 68fa75751e209131cea680ea |

### OPERA

MSE: 0.1705. Result ID: 6993ae213a6c31484917c813.

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

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

Recorded evaluation configuration: {"N":"1000"}. This record does not assert independent reproduction.

### IS

MSE: 0.172. Result ID: 6993ae213a6c31484917c814.

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

Recorded evaluation configuration: {"N":"1000"}. This record does not assert independent reproduction.

### OPERA

MSE: 0.2205. Result ID: 6993ae213a6c31484917c80f.

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

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

Recorded evaluation configuration: {"N":"200"}. This record does not assert independent reproduction.

### FQE

MSE: 0.2448. Result ID: 6993ae213a6c31484917c812.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa55b01e209131ce99623a.md>)

Recorded evaluation configuration: {"N":"200"}. This record does not assert independent reproduction.

### IS

MSE: 0.2753. Result ID: 6993ae213a6c31484917c810.

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

Recorded evaluation configuration: {"N":"200"}. This record does not assert independent reproduction.

### WIS

MSE: 0.2948. Result ID: 6993ae213a6c31484917c815.

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

Recorded evaluation configuration: {"N":"1000"}. This record does not assert independent reproduction.

### FQE

MSE: 0.2995. Result ID: 6993ae213a6c31484917c816.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa55b01e209131ce99623a.md>)

Recorded evaluation configuration: {"N":"1000"}. This record does not assert independent reproduction.

### WIS

MSE: 0.2998. Result ID: 6993ae213a6c31484917c811.

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

Recorded evaluation configuration: {"N":"200"}. This record does not assert independent reproduction.

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