# Action Model Learning on Visual Trace - Blocksworld MNIST grid (test)

Source: [Action Model Learning on Visual Trace - Blocksworld MNIST grid (test)](<https://www.sota2.com/research/sota/action-model-learning-on-visual-trace-blocksworld-mnist-grid-test>)

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

Data updated: 2026-04-23T06:16:45.593Z

Evaluation of Action Model Learning performance on the test split of the Visual Trace - Blocksworld MNIST grid dataset, reporting metrics like Error, Agreement, State Accuracy, and Action 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 Model Learning |
| Dataset (including any stated split) | Visual Trace - Blocksworld MNIST grid (test) |
| Metric | Error |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 1 of 1 |
| 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

- [Error](<https://www.sota2.com/research/sota/action-model-learning-on-visual-trace-blocksworld-mnist-grid-test.md?metric=Error>): Lower is better; unit: SCALAR.

- [Agreement](<https://www.sota2.com/research/sota/action-model-learning-on-visual-trace-blocksworld-mnist-grid-test.md?metric=Agreement>): Higher is better; unit: PERCENT.

- [State Accuracy](<https://www.sota2.com/research/sota/action-model-learning-on-visual-trace-blocksworld-mnist-grid-test.md?metric=State%20Accuracy>): Higher is better; unit: PERCENT.

- [Action Accuracy](<https://www.sota2.com/research/sota/action-model-learning-on-visual-trace-blocksworld-mnist-grid-test.md?metric=Action%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Error | Result date | Report paper |
| --- | --- | --- | --- |
| ROSAME | 0 | Not recorded | 69e85b967d0172140ec80f2e |

### ROSAME

Error: 0. Result ID: 69e9b88f47f34ce924d03843.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b967d0172140ec80f2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85b967d0172140ec80f2e.md>)

Recorded evaluation configuration: {"\|P\|":"36","\|A\|":"50","# Steps":"3","# Fixes":"4","TL(MILP)\[s\]":"60","t/ep\[s\]":"2.50"}. This record does not assert independent reproduction.

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