Drones are being used in real world applications around the world! They can help detect anomalies in crop yields, provide companies with physical assets a real-time continuous data stream, and help secure locations by giving teams an aerial view. We'll learn how a dron can learn to navigate a novel, complex environment using an advanced reinforcement learning technique called Deep Deterministic Policy Gradients. Its a mixture of policy gradients and actor critic, I'll go through the dependencies before explaining the real algorithm. Enjoy!
Code for this video:
https://github.com/llSourcell/Drone_Flight_Controller
Want more education? Connect with me here:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology
instagram: https://www.instagram.com/sirajraval
This video is apart of Move 37, my course at
School of AI:
https://theschool.ai/
Drone 3D Environment:
https://rds.theconstructsim.com/signup/
More learning resources:
https://pemami4911.github.io/blog/2016/08/21/ddpg-rl.html
https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-i-q-learning-sarsa-dqn-ddpg-72a5e0cb6287
https://coach.nervanasys.com/algorithms/policy_optimization/ddpg/index.html
https://towardsdatascience.com/policy-gradients-in-a-nutshell-8b72f9743c5d
https://deepmind.com/research/publications/deterministic-policy-gradient-algorithms/
https://medium.com/@kinwo/solving-continuous-control-environment-using-deep-deterministic-policy-gradient-ddpg-agent-5e94f82f366d
https://medium.freecodecamp.org/an-introduction-to-policy-gradients-with-cartpole-and-doom-495b5ef2207f
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
Please support me on Patreon:
https://www.patreon.com/user?u=3191693
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
