A Journey Into Reinforcement Learning

Monte Carlo Methods

Representing, exploring, and resolving real-world scenarios with machine learning.

Welcome to another chapter to my studies of reinforcement learning. Up until this point, we’ve laid out the foundations of reinforcement learning, describing known environments using finite Markov Decision Processes (MDPs). This is all fine and dandy, until we stumble across a situation where everything about the environment might not be known. This is more interesting…