# Offline Reinforcement Learning on Sepsis MDP n=200

Source: [Offline Reinforcement Learning on Sepsis MDP n=200](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-sepsis-mdp-n-200>)

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

Data updated: 2026-02-26T05:35:59.266Z

Evaluation of Offline Reinforcement Learning algorithms using the Sepsis MDP dataset with N=200 samples.

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) | Sepsis MDP n=200 |
| Metric | Average True Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Average True Return](<https://www.sota2.com/research/sota/offline-reinforcement-learning-on-sepsis-mdp-n-200.md?metric=Average%20True%20Return>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Average True Return | Result date | Report paper |
| --- | --- | --- | --- |
| Optimal Policy | -1.94 | Not recorded | 68fa6e5b1e209131cea3f53f |
| SSR-RRS | -7.85 | Not recorded | 68fa6e5b1e209131cea3f53f |
| CV | -10.26 | Not recorded | 68fa6e5b1e209131cea3f53f |
| SSR-RRS | -13.01 | Not recorded | 68fa6e5b1e209131cea3f53f |
| BVFT-FQE | -19.32 | Not recorded | 68fa6e5b1e209131cea3f53f |
| CV | -20.32 | Not recorded | 68fa6e5b1e209131cea3f53f |

### Optimal Policy

Average True Return: -1.94. Result ID: 69902dd13a6c314849feb05e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

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

### SSR-RRS

Average True Return: -7.85. Result ID: 69902dd13a6c314849feb05d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

[Implementation](<https://github.com/StanfordAI4HI/Split-select-retrain>)

Recorded evaluation configuration: {"repeats":5,"re-trained\_on\_full\_dataset":true}. This record does not assert independent reproduction.

### CV

Average True Return: -10.26. Result ID: 69902dd13a6c314849feb05a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

Recorded evaluation configuration: {"folds":2,"re-trained\_on\_full\_dataset":true}. This record does not assert independent reproduction.

### SSR-RRS

Average True Return: -13.01. Result ID: 69902dd13a6c314849feb05c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

[Implementation](<https://github.com/StanfordAI4HI/Split-select-retrain>)

Recorded evaluation configuration: {"repeats":2,"re-trained\_on\_full\_dataset":true}. This record does not assert independent reproduction.

### BVFT-FQE

Average True Return: -19.32. Result ID: 69902dd13a6c314849feb059.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b291e209131cea2c68b.md>)

Recorded evaluation configuration: {"variant":"pi + FQE","re-trained\_on\_full\_dataset":true}. This record does not assert independent reproduction.

### CV

Average True Return: -20.32. Result ID: 69902dd13a6c314849feb05b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f53f.md>)

Recorded evaluation configuration: {"folds":5,"re-trained\_on\_full\_dataset":true}. This record does not assert independent reproduction.

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