Inspired and motivated by "DEEP MIND" to learn and apply Reinforcement Learning. This is a simple model to demonstrate the understanding and working of Reinforcement Learning, using OPEN AI GYM'S "CartPole-v1" environment and SEQUENTIAL NEURAL NETWORK model from keras. A type of Learning different than ML, where the model learns and improve itself from mistakes in the environment, without providing tons of data to improve.
Reinforcement learning:
It can be a little tricky to get all setup with RL. You need to manage environments, build your DL models and work out how to save your models down so you can reuse them. But that shouldn’t stop you!
Why?
Because they’re powering the next generation of advancements in IOT environments and even gaming and the use cases for RL are growing by the minute. That being said, getting started doesn’t need to be a pain, you can get up and running in just 20 minutes working with Keras-RL and OpenAI.
Steps are:-
- Create OpenAI Gym environments CartPole
- Building a Deep Learning model for Reinforcement Learning using Tensorflow and Keras
- Training and testing a Reinforcement Learning model using Deep Q Policy based learning using Keras-RL
- Save the model weights and reload it whenever needed.
Developed with the help of Nicholas Renotte youtube channel.