# Learning in novel environments on NS novel environments n=8K (test)

Source: [Learning in novel environments on NS novel environments n=8K (test)](<https://www.sota2.com/research/sota/learning-in-novel-environments-on-ns-novel-environments-n-8k-test>)

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

Data updated: 2026-02-26T06:06:19.206Z

Evaluation of model performance on learning and generalization within the NS novel environments dataset (n=8K test split), typically measured using Mean Squared Error (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 | Learning in novel environments |
| Dataset (including any stated split) | NS novel environments n=8K (test) |
| Metric | Test MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [Test MSE](<https://www.sota2.com/research/sota/learning-in-novel-environments-on-ns-novel-environments-n-8k-test.md?metric=Test%20MSE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Test MSE | Result date | Report paper |
| --- | --- | --- | --- |
| Pre-trained-f-Plus-Trained-ge | 0.00714 | Not recorded | 68fa6bd81e209131cea30887 |
| Pre-trained-f-Plus-Trained-ge | 0.00807 | Not recorded | 68fa6bd81e209131cea30887 |
| One-Per-Env. from scratch | 0.0118 | Not recorded | 68fa6bd81e209131cea30887 |
| Pre-trained-f-Plus-Trained-ge | 0.0137 | Not recorded | 68fa6bd81e209131cea30887 |
| One-Per-Env. from scratch | 0.017 | Not recorded | 68fa6bd81e209131cea30887 |
| One-Per-Env. from scratch | 0.0676 | Not recorded | 68fa6bd81e209131cea30887 |
| Pre-trained-f-Only | 0.175 | Not recorded | 68fa6bd81e209131cea30887 |
| Pre-trained-f-Only | 0.175 | Not recorded | 68fa6bd81e209131cea30887 |
| Pre-trained-f-Only | 0.175 | Not recorded | 68fa6bd81e209131cea30887 |

### Pre-trained-f-Plus-Trained-ge

Test MSE: 0.00714. Result ID: 698ea53dffc3901de09f6b9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Implementation](<https://github.com/yuan-yin/LEADS>)

Recorded evaluation configuration: {"Training step":"10000"}. This record does not assert independent reproduction.

### Pre-trained-f-Plus-Trained-ge

Test MSE: 0.00807. Result ID: 698ea53dffc3901de09f6b99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Implementation](<https://github.com/yuan-yin/LEADS>)

Recorded evaluation configuration: {"Training step":"2500"}. This record does not assert independent reproduction.

### One-Per-Env. from scratch

Test MSE: 0.0118. Result ID: 698ea53dffc3901de09f6b97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"10000"}. This record does not assert independent reproduction.

### Pre-trained-f-Plus-Trained-ge

Test MSE: 0.0137. Result ID: 698ea53dffc3901de09f6b98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

[Implementation](<https://github.com/yuan-yin/LEADS>)

Recorded evaluation configuration: {"Training step":"50"}. This record does not assert independent reproduction.

### One-Per-Env. from scratch

Test MSE: 0.017. Result ID: 698ea53dffc3901de09f6b96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"2500"}. This record does not assert independent reproduction.

### One-Per-Env. from scratch

Test MSE: 0.0676. Result ID: 698ea53dffc3901de09f6b95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"50"}. This record does not assert independent reproduction.

### Pre-trained-f-Only

Test MSE: 0.175. Result ID: 698ea53dffc3901de09f6b92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"50"}. This record does not assert independent reproduction.

### Pre-trained-f-Only

Test MSE: 0.175. Result ID: 698ea53dffc3901de09f6b93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"2500"}. This record does not assert independent reproduction.

### Pre-trained-f-Only

Test MSE: 0.175. Result ID: 698ea53dffc3901de09f6b94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30887.md>)

Recorded evaluation configuration: {"Training step":"10000"}. This record does not assert independent reproduction.

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