1. Introduction and Outline

  1. Introduction and outline.vtt

  2. What is Reinforcement Learning.vtt

  3. Where to get the Code.vtt

  4. Strategy for Passing the Course.vtt

 2. Return of the Multi-Armed Bandit

  1. Problem Setup and The Explore-Exploit Dilemma.vtt

  2. Epsilon-Greedy.vtt

  3. Updating a Sample Mean.vtt

  4. Comparing Different Epsilons.vtt

  5. Optimistic Initial Values.vtt

  6. UCB1.vtt

  7. Bayesian Thompson Sampling.vtt

  8. Thompson Sampling vs. Epsilon-Greedy vs. Optimistic Initial Values vs. UCB1.vtt

  9. Nonstationary Bandits.vtt

 3. Build an Intelligent Tic-Tac-Toe Agent

  1. Naive Solution to Tic-Tac-Toe.vtt

  10. Tic Tac Toe Code Main Loop and Demo.vtt

  11. Tic Tac Toe Summary.vtt

  2. Components of a Reinforcement Learning System.vtt

  3. Notes on Assigning Rewards.vtt

  4. The Value Function and Your First Reinforcement Learning Algorithm.vtt

  5. Tic Tac Toe Code Outline.vtt

  6. Tic Tac Toe Code Representing States.vtt

  7. Tic Tac Toe Code Enumerating States Recursively.vtt

  8. Tic Tac Toe Code The Environment.vtt

  9. Tic Tac Toe Code The Agent.vtt

 4. Markov Decision Proccesses

  1. Gridworld.vtt

  2. The Markov Property.vtt

  3. Defining and Formalizing the MDP.vtt

  4. Future Rewards.vtt

  5. Value Function Introduction.vtt

  6. Value Functions.vtt

  7. Bellman Examples.vtt

  8. Optimal Policy and Optimal Value Function.vtt

  9. MDP Summary.vtt

 5. Dynamic Programming

  1. Intro to Dynamic Programming and Iterative Policy Evaluation.vtt

  10. Dynamic Programming Summary.vtt

  2. Gridworld in Code.vtt

  3. Iterative Policy Evaluation in Code.vtt

  4. Policy Improvement.vtt

  5. Policy Iteration.vtt

  6. Policy Iteration in Code.vtt

  7. Policy Iteration in Windy Gridworld.vtt

  8. Value Iteration.vtt

  9. Value Iteration in Code.vtt

 6. Monte Carlo

  1. Monte Carlo Intro.vtt

  2. Monte Carlo Policy Evaluation.vtt

  3. Monte Carlo Policy Evaluation in Code.vtt

  4. Policy Evaluation in Windy Gridworld.vtt

  5. Monte Carlo Control.vtt

  6. Monte Carlo Control in Code.vtt

  7. Monte Carlo Control without Exploring Starts.vtt

  8. Monte Carlo Control without Exploring Starts in Code.vtt

  9. Monte Carlo Summary.vtt

 7. Temporal Difference Learning

  1. Temporal Difference Intro.vtt

  2. TD(0) Prediction.vtt

  3. TD(0) Prediction in Code.vtt

  4. SARSA.vtt

  5. SARSA in Code.vtt

  6. Q Learning.vtt

  7. Q Learning in Code.vtt

  8. TD Summary.vtt

 8. Approximation Methods

  1. Approximation Intro.vtt

  2. Linear Models for Reinforcement Learning.vtt

  3. Features.vtt

  4. Monte Carlo Prediction with Approximation.vtt

  5. Monte Carlo Prediction with Approximation in Code.vtt

  6. TD(0) Semi-Gradient Prediction.vtt

  7. Semi-Gradient SARSA.vtt

  8. Semi-Gradient SARSA in Code.vtt

  9. Course Summary and Next Steps.vtt

 9. Appendix

  1. What is the Appendix.vtt

  10. What order should I take your courses in (part 1).vtt

  11. What order should I take your courses in (part 2).vtt

  12. Where to get discount coupons and FREE deep learning material.vtt

  2. Windows-Focused Environment Setup 2018.vtt

  3. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.vtt

  4. How to Code by Yourself (part 1).vtt

  5. How to Code by Yourself (part 2).vtt

  6. How to Succeed in this Course (Long Version).vtt

  7. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.vtt

  8. Proof that using Jupyter Notebook is the same as not using it.vtt

  9. Python 2 vs Python 3.vtt

 [CourseClub.NET].url

 [FreeCourseSite.com].url