Deep Q Learning is Simple with Tensorflow

Simple Deep Q Network w/Pytorch:
Reinforcement Learning Crash Course:
Policy Gradients w/Tensorflow
Deep Q Learning w/Tensorflow
Code Your Own RL Environments
How to Spec a Deep Learning PC:
Deep Q Learning w/ Pytorch:
Machine Learning Freelancing

#DeepQLearning #Tensorflow #LunarLander

In this tutorial, we're going to code the simplest possible deep Q network, using the Tensorflow framework. In previous tutorials we used something called double q learning, where we had two networks. One network to calculate the value of the current state, and another network to calculate the values of the next states.

It turns out you don't actually have to go to such great lengths, and can achieve great performance with just a single network.

You are going to demonstrate that using the Lunar Lander environment from the Open AI gym. In just 500 games we'll have an agent that can land safely within the flags, thus effectively beating the environment.

Twitter:
Github:
Website:
Course:

deep q learning,deep q learning tutorial,deep q learning example,deep q learning algorithm,deep q learning tensorflow,deep q learning explained,deep q learning lunar lander,q learning,q learning tutorial,q learning example,q learning algorithm,q learning tensorflow,q learning explained,q learning lunar lander,openai gym,tensorflow tutorial,