The Markov Decision Process is the formal description of the Reinforcement Learning problem. It includes concepts like states, actions, rewards, and how an agent makes decisions based on a given policy. So, what Reinforcement Learning algorithms do is to find optimal solutions to Markov Decision Processes.
Because it is a fundamental concept in the Reinforcement Learning domain, we selected more than 40 resources about Markov Decision Process, including blog posts, books, and videos. Check the links below.
Blog Posts
- Reinforcement Learning Demystified: Markov Decision Processes (Part 1)
- Reinforcement Learning Demystified: Markov Decision Processes (Part 2)
- RL part 3. Markov Decision Process, policy, Bellman Optimality Equation.
- AN INTRODUCTION TO REINFORCEMENT LEARNING – I :: MARKOV DECISION PROCESSES
- Markov Decision Processes, by Applied Probability Notes
- Markov Decision Process for Tic Tac Toe
- Self Learning AI-Agents Part I: Markov Decision Processes
- Getting Started with Markov Decision Processes: Reinforcement Learning
- Understanding Markov Decision Processes
- Markov chains and Markov Decision process
- Not-So-Deep Reinforcement Learning for dummies — Part 2
- Markov Decision process
Books
- Markov Decision Processes: Discrete Stochastic Dynamic Programming
- Continuous-Time Markov Decision Processes
- Planning with Markov Decision Processes: An AI Perspective
- Markov Decision Processes in Practice
- Constrained Markov Decision Processes
- Reinforcement Learning, an Introduction
Top comments (0)