Hey there. Here is a paper I wrote on autonomous agents that autonomously navigate the desktop user interfaces.
“Towards Automated Exploration of Interactive Systems”
Sorry it’s not on arXiv right now. Here’s the PDF: https://faculty.cc.gatech.edu/~riedl/pubs/iui02.pdf
“Towards Automated Exploration of Interactive Systems”
Sorry it’s not on arXiv right now. Here’s the PDF: https://faculty.cc.gatech.edu/~riedl/pubs/iui02.pdf
Comments
We used a very basic vision system operating on pixel-level input and the ACT-R cognitive architecture that learned how to find and use UI operations