# Action Selection Task (AST) on SGD (out-of-distribution)

Source: [Action Selection Task (AST) on SGD (out-of-distribution)](<https://www.sota2.com/research/sota/action-selection-task-ast-on-sgd-out-of-distribution>)

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

Data updated: 2026-02-26T05:36:34.370Z

Evaluation of the Action Selection Task (AST) performance on the out-of-distribution split of the SGD dataset, measured by B-Slot accuracy and Value accuracy.

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 | Action Selection Task (AST) |
| Dataset (including any stated split) | SGD (out-of-distribution) |
| Metric | B-Slot Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [B-Slot Acc](<https://www.sota2.com/research/sota/action-selection-task-ast-on-sgd-out-of-distribution.md?metric=B-Slot%20Acc>): Higher is better; unit: PERCENT.

- [Value Acc](<https://www.sota2.com/research/sota/action-selection-task-ast-on-sgd-out-of-distribution.md?metric=Value%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | B-Slot Acc | Result date | Report paper |
| --- | --- | --- | --- |
| full data | 61.3 | Not recorded | 68fa6f9c1e209131cea46964 |
| KADS | 49.8 | Not recorded | 68fa6f9c1e209131cea46964 |
| T5 | 46.2 | Not recorded | 68fa6f9c1e209131cea46964 |

### full data

B-Slot Acc: 61.3. Result ID: 6990cf723a6c314849037449.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9c1e209131cea46964.md>)

Recorded evaluation configuration: {"training\_protocol":"in-distribution"}. This record does not assert independent reproduction.

### KADS

B-Slot Acc: 49.8. Result ID: 6990cf723a6c314849037448.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9c1e209131cea46964.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f9c1e209131cea46964.md>)

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

### T5

B-Slot Acc: 46.2. Result ID: 6990cf723a6c314849037447.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f9c1e209131cea46964.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"guided":false}. This record does not assert independent reproduction.

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