CSE190: Computational Techniques in Robotics (Final Project)
As a final project, I implementing reinforcement learning as an extension to my Robot Simulation. More specifically, I am implementing Q-Learning, which can be used to find an optimal action-selection policy for any given Markov decision process. It uses an action-value function which gives the expected utility of taking a given action in a given state and following the optimal policy as a result. In this case, the probabilistic models used to solve the Markov Decision Process problem are not known and have not been learned.
This project utilized knowledge learned from the course, including the Robot Operating System (ROS).