Machine Learning Engineer Nanodegree - Tarun Parmar

Reinforcement Learning

Project: Train a Samrtcab to Drive

Project Overview

In this project we will apply reinforcement learning techniques for a self-driving agent in a simplified world to aid it in effectively reaching its destinations in the allotted time. We will first investigate the environment the agent operates in by constructing a very basic driving implementation. Once our agent is successful at operating within the environment, we will then identify each possible state the agent can be in when considering such things as traffic lights and oncoming traffic at each intersection. With states identified, we will then implement a Q-Learning algorithm for the self-driving agent to guide the agent towards its destination within the allotted time. Finally, we will improve upon the Q-Learning algorithm to find the best configuration of learning and exploration factors to ensure the self-driving agent is reaching its destinations with consistently positive results.