Intermediate Reinforcement Learning Techniques
Chapter 1: Revisiting Reinforcement Learning Fundamentals
The Reinforcement Learning Problem Setup
Markov Decision Processes (MDPs) Recap
Value Functions and Bellman Equations
Tabular Solution Methods: Q-Learning and SARSA
Limitations of Tabular Methods
Quiz for Chapter 1
Chapter 2: Deep Q-Networks (DQN)
Introduction to Function Approximation
Using Neural Networks for Q-Value Approximation
The DQN Algorithm Architecture
Experience Replay Mechanism
Fixed Q-Targets (Target Networks)
Loss Function for DQN Training
Hands-on Practical: Implementing DQN for CartPole
Quiz for Chapter 2
Chapter 3: Improvements and Variants of DQN
The Overestimation Problem in Q-Learning
Double DQN (DDQN)
Dueling Network Architectures
Combining DQN Improvements
Prioritized Experience Replay (Brief Overview)
Practice: Implementing Double DQN
Quiz for Chapter 3
Chapter 4: Policy Gradient Methods
Limitations of Value-Based Methods
Direct Policy Parameterization
The Policy Gradient Theorem
REINFORCE Algorithm
Understanding Variance in Policy Gradients
Baselines for Variance Reduction
Hands-on Practical: Implementing REINFORCE
Quiz for Chapter 4
Chapter 5: Actor-Critic Methods
Combining Policy and Value Estimation
Actor-Critic Architecture Overview
Advantage Actor-Critic (A2C)
Asynchronous Advantage Actor-Critic (A3C)
Implementation Considerations for Actor-Critic
Comparison: REINFORCE vs A2C/A3C
Practice: Developing an A2C Implementation
Quiz for Chapter 5
Limitations of Value-Based Methods
Was this section helpful?
- Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto, 2018 (The MIT Press) - A foundational textbook covering both value-based and policy gradient methods, explaining their principles and the scenarios where policy gradient methods offer advantages, such as handling continuous action spaces and learning stochastic policies.
- Continuous Control with Deep Reinforcement Learning, Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra, 2015 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1509.02971 - Introduces Deep Deterministic Policy Gradient (DDPG), an algorithm specifically designed for continuous action spaces, which directly addresses a significant limitation of traditional value-based methods like DQN.
- Proximal Policy Optimization Algorithms, John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov, 2017 DOI: 10.48550/arXiv.1707.06347 - Presents Proximal Policy Optimization (PPO), a widely used and robust policy gradient algorithm known for its performance in various continuous and discrete control tasks, showcasing the effectiveness of direct policy optimization.