Published September 25, 2023
| Version 1.0.0
Software
Open
CAT optimal hybrid solver
Creators
- 1. Università della Svizzera Italiana (USI), Switzerland
-
2.
Dalle Molle Institute for Artificial Intelligence Research
Contributors
Supervisor:
- 1. Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, Switzerland
Description
The CAT Optimal Hybrid Solver is a tool designed to tackle the cross array task (CAT) activity designed to assess algorithmic thinking skills in the context of K-12 education. This software utilizes a hybrid approach that combines clustering, random search, and reinforcement learning techniques to identify optimal or sub-optimal solutions for CAT.
The primary goal of this software is to assist students in the CAT activity by suggesting their next moves, thereby improving their computational thinking and problem-solving abilities. It can be seamlessly integrated into existing educational tools to offer personalized support to students, helping them overcome challenges in completing the CAT.
Files
GiorgiaAuroraAdorni/CAT-optimal-hybrid-solver-1.0.0.zip
Files
(40.6 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:10201e110eb21f731539a9cb32a67980
|
40.6 MB | Preview Download |
Additional details
Related works
- Is cited by
- Journal article: 10.3390/make5040082 (DOI)
- Is supplement to
- Software: https://github.com/GiorgiaAuroraAdorni/CAT-optimal-hybrid-solver/tree/1.0.0 (URL)
- References
- Journal article: 10.1016/j.chbr.2021.100166 (DOI)
Funding
- Assessing the development of computational thinking skills through an intelligent tutoring system: an exploratory study in the cantons of St Gallen, Vaud and Ticino. 407740_187246
- Swiss National Science Foundation
References
- A. Piatti, G. Adorni, L. El-Hamamsy, L. Negrini, D. Assaf, L. Gambardella & F. Mondada. (2022). The CT-cube: A framework for the design and the assessment of computational thinking activities. Computers in Human Behavior Reports, 5, 100166. https://doi.org/10.1016/j.chbr.2021.100166
- Corecco, S.; Adorni, G.; Gambardella, L.M. Proximal Policy Optimization-Based Reinforcement Learning and Hybrid Approaches to Explore the Cross Array Task Optimal Solution. Mach. Learn. Knowl. Extr. 2023, 5, 1660-1679. https://doi.org/10.3390/make5040082