I'll show you how to code a Deep Q Learning agent using tensorflow 2 from scratch. You don't need any prior reinforcement learning experience, we'll cover everything you need as we go. The deep Q learning algorithm is quite effective at solving even very complex environments, and even the reduced implementation we're coding up today is sufficient for non trivial environments like the lunar lander from the open AI gym.
You'll see how to code a replay memory as well as to code up a sequential model in keras / tensorflow 2. We'll cover some basic principles of object oriented python programming, and wrap it up with a review of the agent's performance.
Learn all about deep Q learning and its variations in my new course, on sale for $10 for a limited time.
https://www.udemy.com/course/actor-critic-methods-from-paper-to-code-with-pytorch/?couponCode=MAY-20-1
Courses:
https://www.manning.com/livevideo/reinforcement-learning-in-motion
https://www.udemy.com/course/actor-critic-methods-from-paper-to-code-with-pytorch/?couponCode=MAY-20-1
Website: https://www.neuralnet.ai
Github: https://github.com/philtabor
Twitter: https://twitter.com/MLWithPhil
#Tensorflow2 #OpenAIGym #DeepQLearning