ML Book 9 - Reinforcement Learning/ Algorithms and Applications for Rookies

Table of Contents

1. Introduction

1.1 What is Reinforcement Learning?

1.2 The Reinforcement Learning Problem

1.3 Examples of Reinforcement Learning Applications

1.4 Challenges and Opportunities in Reinforcement Learning 2. Basic Concepts and Terminology

2.1 Agents and Environments

2.2 Rewards and Returns

2.3 Policies and Value Functions

2.4 Markov Decision Processes

2.5 Exploration and Exploitation

3. Dynamic Programming Methods

3.1 Policy Evaluation

3.2 Policy Improvement

3.3 Policy Iteration

3.4 Value Iteration

3.5 Limitations and Extensions of Dynamic Programming

4. Monte Carlo Methods

4.1 Monte Carlo Prediction

4.2 Monte Carlo Control

4.3 Monte Carlo with Function Approximation

4.4 Monte Carlo in Continuous Spaces

4.5 Monte Carlo for Partially Observable Environments

5. Temporal Difference Methods

5.1 TD Prediction

5.2 TD Control: SARSA and Q-learning

5.3 TD with Function Approximation

5.4 TD in Continuous Spaces

5.5 TD for Partially Observable Environments

6. Policy Gradient Methods

6.1 Policy Gradient Theorem

6.2 REINFORCE Algorithm

6.3 Actor-Critic Methods

6.4 Policy Gradient with Function Approximation

6.5 Policy Gradient in Continuous Spaces

7. Advanced Topics and Applications

7.1 Multi-Agent Reinforcement Learning

7.2 Hierarchical Reinforcement Learning

7.3 Inverse Reinforcement Learning

7.4 Reinforcement Learning for Robotics

7.5 Reinforcement Learning for Games