In reinforcement learning, self-learning agent learns how to interact with the environment and solve a problem within it. In this article, we present complete guide to reinforcemen learning and one type of it Q-Learning (which with the help of deep learning become Deep Q-Learning). We learn about the inspiration behind this type of learning and implement it with Python, TensorFlow and TensorFlow Agents. By Nikola M. Zivkovic.
In supervised learning, an agent learns how to map certain inputs to some output. The agent learns how to do that because during the learning process it is provided with training inputs and labeled expected outputs for those inputs. Using this approach we are able to solve many types of problems, mostly the ones which are classification and regression problems in nature. This is an important type of learning and it is mostly used commercial approach today.
Here are the topics that author covers in this article:
- Introduction to Reinforcement Learning
- Q-Learning Intuition
- Q-Learning implementation with Python
- Deep-Q Learning Intuition
- Deep-Q Learning implementation with TensorFlow
In this article we explored Deep Q-Learning. This is the first type of reinforcement learning that utilize neural networks. Plenty of code examples in Python in the article. Good read!
[Read More]