Reproduce “Narrowing Action Choices with AI Improves Human Sequential Decisions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Eleni Straitouri, Stratis Tsirtsis, Ander Artola Velasco, Manuel Gomez-Rodriguez
The system supports people containing a spreading fire on a forest grid by restricting their choices to a menu of highly ranked actions, with a tunable menu width. In a study of 1,600 participants, the best setting achieved 29.65% higher average discounted cumulative reward than unaided play and 2.31% higher than the AI alone, in this game only.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.