Training and test data for the Maze experiments in Scale-Equalized Rollout Allocation (SERA).
Rows7,824
Configurations1
Size9.3 MB
License—
AccessPublicly accessible
Monthly Downloads—
Dataset Card
Training and test data for the Maze experiments in Scale-Equalized Rollout Allocation (SERA).
Excerpt from the card by Zihao Chen.
Structure
default 7,824 rows
| Split | Rows | Size |
|---|---|---|
| train | 7,424 | 50.9 MB |
| test | 400 | 2.8 MB |
data_sourcestringpromptlistabilitystringreward_modelvalueextra_infovalue
Details
- Repository
- capybaraczh/SERA-Maze-17x17
- Publisher
- Zihao Chen
- Task category
- Not stated by the source
- Tags
- maze, reinforcement-learning, sera
- Size category
- 1K<n<10K
- Languages
- Not stated by the source
- Revision
- 8435e3ffbb08b45f6b44c08bc50d37869e294e06
- Last updated
- 2026-09-28
Files
4 files, 9.3 MB in total.
Data2 files · 9.3 MB
Documentation1 file · 1.0 KB
Repository1 file · 2.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| test.parquet | Data | 495.5 KB | b9118c1e9e91 |
| train.parquet | Data | 8.8 MB | b523486c3d4f |
| README.md | Documentation | 1.0 KB | — |
| .gitattributes | Repository | 2.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- No access gate
Download from Zihao Chen
Released by Zihao Chen through its official repository on Hugging Face.