Reinforcement Learning with Python

Introduction: Reinforcement Learning

Some RL success stories

Welcome to Reinforcement Learning

1. An example: OpenAI Gym
2. Using a different policy
3. Your turn:

Markov Decision Processes

1. Markov chains
2. Markov Reward Process
3. Markov Decision Processes
4. Solving MDPs: Value and Policy Iteration.

Chapter 3: Monte Carlo Methods

1. Monte Carlo Learning
2. Off-policy MC control

Chapter 4: Temporal Difference Learning

1. Code sample: SARSA

Chapter 5: Function approximation.

1. Gradient descent
2. Feature vectors
3. Function backups
4. Code sample: SARSA with linear function approximation

Chapter 6: Experience Replay.

1. Improvements since the original DQN
2. #
3. Code sample: Q-Learning with experience replay (Linear Approximator)
4. Code sample: Q-Learning with experience replay (Neural Network Approximator)

Chapter 7: Policy Gradients & Policy Optimisation

1. Derivative Free Methods
2. Code sample: NES for FrozenLake
3. Code sample: Cross entropy method for CartPole

About the author