To realize the full potential of AI, autonomous systems must learn to make good decisions. Reinforcement Learning (RL) is a powerful paradigm for training systems in decision making. RL algorithms are applicable to a wide range of tasks, including robotics, game playing, consumer modeling, and healthcare.

In this course, you will gain a solid introduction to the field of reinforcement learning. Through a combination of lectures and coding assignments, you will learn about the core approaches and challenges in the field, including generalization and exploration. You will also have a chance to explore the concept of deep reinforcement learning—an extremely promising new area that combines reinforcement learning with deep learning techniques.

  • Find the best strategies in an unknown environment using Markov decision processes, Monte Carlo policy evaluation, and other tabular solution methods.
  • Design and implement reinforcement learning algorithms on a larger scale with linear value function approximation and deep reinforcement learning techniques.
  • Model and optimize your strategies with policy-based reinforcement learning such as score functions, policy gradient, and REINFORCE.
  • Evaluate and enhance your reinforcement learning algorithms with bandits and MDPs.
  • Maximize learnings from a static dataset using offline and batch reinforcement learning methods.