Keras Reinforcement Learning Projects
by Giuseppe Ciaburro, Sudharsan Ravichandiran, Suriyadeepan Ramamoorthy
The Keras–RL package
In the previous sections, we learned how to make a simple neural network with Keras. But, our goal is to develop algorithms based on reinforcement learning in the Keras environment. To do this, a valid tool that can be used is the keras-rl package. This package implements some deep reinforcement learning algorithms in Python, and integrates seamlessly with Keras's in-depth learning library.
Furthermore, keras-rl works immediately with OpenAI Gym. OpenAI Gym is a library that helps you implement algorithms based on reinforcement learning. It includes a growing collection of benchmark issues that expose a common interface and a website where people can share their results and compare algorithm performance. This library ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access