Code samples for Deep Reinforcement Learning Hands-On book
This repository is being maintained by book author Max Lapan. I'm trying to keep all the examples working under the latest versions of PyTorch and gym, which is not always simple, as software evolves. For example, OpenAI Universe, extensively being used in chapter 13, was discontinued by OpenAI. List of current requirements is present in requirements.txt file.
Examples require python 3.6.
And, of course, bugs in examples are inevitable, so, exact code might differ from code present in the book text.
Too keep track of major code change, I'm using tags and branches, for example:
Recent developments in reinforcement learning (RL), combined with deep learning (DL), have seen unprecedented progress made towards training agents to solve complex problems in a human-like way. Google’s use of algorithms to play and defeat the well-known Atari arcade games has propelled the field to prominence, and researchers are generating new ideas at a rapid pace.
Deep Reinforcement Learning Hands-On is a comprehensive guide to the very latest DL tools and their limitations. You will evaluate methods including Cross-entropy and policy gradients, before applying them to real-world environments. Take on both the Atari set of virtual games and family favorites such as Connect4. The book provides an introduction to the basics of RL, giving you the know-how to code intelligent learning agents to take on a formidable array of practical tasks. Discover how to implement Q-learning on ‘grid world’ environments, teach your agent to buy and trade stocks, and find out how natural language models are driving the boom in chatbots.