My interest in machine learning speckles this website, but I've become especially fascinated by computer agents capable of mimicking human-like decision making in constrained environments.
Through my Teach-It projects, I aspire to collect data about human players, train a variety of machine learning agents using that data, and develop agents with a preference for "human" approaches over perfectly optimized approaches.
(But why "human" approaches?: 35:04 to 39:31)
The Teach-IT collection is being reimagined (e.g., scalable infrastructure, faster predictions, improvements to aesthetic - ease of use - and analytics, etc.), and I look forward to sharing those developments when the reimagining and refactoring are further along.
This website uses cookies. By continuing to use this site, you accept our use of cookies.