I'm Ryan, a Computer Science student
and Reinforcement Learning enthusiast.
Monte-Carlo Learning is an RL method used to estimate value functions and discover optimal policies for unknown MDPs. A great way to understand its concepts is with the card game Blackjack.View Project
Dynamic Programming is a fundamental technique in Reinforcement Learning, used for breaking complex problems down into subproblems to solve finite MDPs. This project focuses on three different methods.View Project
Wild Edible Plant Classifier
With the need for an increase in food resources before the year 2050, it’s crucial to consider alternative food sources. Convolutional Neural Networks can help achieve this!View Project