Reinforcement Learning (RL) is a type of machine learning where an agent (e.g. a robot) learns to make decisions by taking actions in an environment to maximize some notion of cumulative reward. RL is a crucial component for building autonomous systems that can improve over time.
RL has been used to achieve breakthroughs in a variety of fields. The most famous example is AlphaGo, which eventually beat the best human Go player in the world. Since then, it has found applications in stock trading, robotics, game playing, and resource management among others.
You will go over foundational principles and concepts in reinforcement learning and understand how agents interact with their environment. You will be introduced to concepts such as state, action, reward, and policy/value functions. You'll get to understand the problem setup of reinforcement learning and how it differs from other types of machine learning.
Markov Decision Processes (MDPs): MDPs are mathematical frameworks used to describe interactions between agents and the environment in reinforcement learning. They're essential for understanding how decisions made now can influence future outcomes.
Q Learning: Q-learning is a values-based algorithm in reinforcement learning, used to determine the optimal action-selection policy using a Q function. You'll learn how to implement it and when it's advantageous to use. You'll then move onto Deep Q-Learning which combines Q-Learning with deep learning, enabling the handling of complex, high-dimensional environments.
Our curriculum was designed for students with at least a pre-calculus background. You'll definitely learn more about math during these lessons, but it shouldn't be anything overly complicated. We've done a careful job balancing both depth of the material vs difficulty.