Draichi/reinforcement-learning-specialization

Course specialization notebooks

Reinforcement Learning Specialization

Table of Contents

• Fundamentals of Reinforcement Learning

  • Bandits and Exploration/Exploitation
  • Optimal Policies with Dynamic Programming

• Sample-based Learning Methods

  • Policy Evaluation in Cliff Walking Environment
  • Q-Learning and Expected Sarsa on a Cliff World
  • Dyna-Q and Dyna-Q+

• Prediction and Control With Function Approximation

  • Semi-Gradient TD(0) with State Aggregation