Reinforcement Learning

Reinforcement Learning Specialization

• Fundamentals of Reinforcement Learning
  • Week 1
    • Practice Quiz: Exploration-Exploitation
    • Notebook: Bandits and Exploration/Exploitation
  • Week 2
    • Practice Quiz: MDPs
  • Week 3
    • Practice Quiz: Value Functions and Bellman Equations
    • Quiz: Value Functions and Bellman Equations
  • Week 4
    • Practice Quiz: Dynamic Programming
    • Notebook: Optimal Policies with Dynamic Programming
• Sample-based Learning Methods
  • Week 2
    • Quiz: Graded Quiz
    • Notebook: Blackjack
  • Week 3
    • Quiz: Practice Quiz
    • Notebook: Policy Evaluation with Temporal Difference Learning
  • Week 4
    • Quiz: Practice Quiz
    • Notebook: Q-Learning and Expected Sarsa
  • Week 5
    • Quiz: Practice Assessment
    • Notebook: Dyna-Q and Dyna-Q+
• Prediction and Control with Function Approximation
  • Week 1
    • Practice Quiz: On-policy Prediction with Approximation
    • Notebook: Semi-gradient TD(0) with State Aggregation
  • Week 2
    • Practice Quiz: Constructing Features for Prediction
    • Notebook: Semi-gradient TD with a Neural Network
  • Week 3
    • Practice Quiz: Control with Approximation
    • Notebook: Function Approximation and Control
  • Week 4
    • Practice Quiz: Policy Gradient Methods
    • Notebook: Average Reward Softmax Actor-Critic using Tile-coding
• A Complete Reinforcement Learning System (Capstone)
  • Week 2
    • Notebook: MoonShot Technologies
  • Week 3
    • Quiz: Choosing the Right Algorithm
  • Week 4
    • Quiz: Impact of Parameter Choices in RL
  • Week 5
    • Notebook: Implement Your Agent
  • Week 6
    • Notebook: Completing the parameter study

Instructors: Martha White and Adam White

These course materials belong entirely to University of Alberta & Alberta Machine Intelligence Institute. The solutions are only mine.

Reference Materials:

• https://github.com/dennybritz/reinforcement-learning
• https://github.com/ShangtongZhang/reinforcement-learning-an-introduction
• https://github.com/LyWangPX/Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions
• David Silver Reinforcement Learning course - slides, YouTube-playlist