Artificial Intelligence IV – Reinforcement Learning in Java
All you need to know about Markov Decision processes, value- and policy-iteation as well as about Q learning approach
Understand reinforcement learning
Understand Markov Decision Processes
Understand value- and policy-iteration
Understand Q-learning approach and it's applications
This course is about Reinforcement Learning. The first step is to talk about the mathematical background: we can use a Markov Decision Process as a model for reinforcement learning. We can solve the problem 3 ways: value-iteration, policy-iteration and Q-learning. Q-learning is a model free approach so it is state-of-the-art approach. It learns the optimal policy by interacting with the environment. So these are the topics:
- Markov Decision Processes
- value-iteration and policy-iteration
- Q-learning fundamentals
- pathfinding algorithms with Q-learning
- Q-learning with neural networks
Introduction
1
Introduction
2
Types of learning
3
Applications of reinforcement learning
Markov Decision Process (MDP) Theory
1
Markov decision processes basics I
2
Markov decision processes basics II
3
Markov decision processes - equations
4
Markov decision processes - illustration
5
Bellman-equation
6
How to solve MDP problems?
7
Mathematical formulation of reinforcement learning
8
Reinforcement Learning Basics Quiz
Markov Decision Process - Value Iteration
1
What is value iteration?
2
Value iteration implementation I
3
Value iteration implementation II
4
Value iteration implementation III
5
Value iteration implementation IV
6
Value iteration implementation V
Markov Decision Process - Policy Iteration
1
What is policy iteration?
2
Value iteration vs policy iteration
Q Learning Theory
1
Q learning introduction
2
Q learning introduction - the algorithm
3
Q learning illustration
4
Mathematical formulation of Q learning
5
Q Learning Quiz
Pathfinding with Q-Learning
1
---- PATHFINDING ----
2
Pathfinding with Q-learning I
3
Pathfinding with Q-learning II
4
Pathfinding with Q-learning III
5
Pathfinding with Q-learning IV
6
---- SHORTEST PATH ----
7
Shortest path with Q-learning
Exploration vs. Exploitation Problem
1
Exploration vs exploitation problem
2
N-armed bandit problem introduction
3
N-armed bandit problem implementation I
4
N-armed bandit problem implementation II
5
Applications: A/B testing in marketing
6
Exploration vs. Exploitation Quiz
Deep Reinforcement Learning Theory
1
What is deep Q learning?
2
Deep Q learning and ε-greedy strategy
3
Deep Q-learning introduction - remember and replay
4
Mathematical formulation of deep Q learning
5
Deep Q Learning Quiz
Course Materials (DOWNLOADS)
1
Course materials
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
Includes
3 hours on-demand video
6 articles
1 lectures
Certificate of Completion
