Learning Goals
Learn the concept of Reinforcement learning by solving the cartpole player problem with the use of OpenAI gym.
Exercise Statement
This exercise helps in learning reinforcement learning using 2 approaches. First, using random playing strategy multiple times and saving parameters for the best average episode. Second, using Deep Q-Learning strategy to optimize the parameters, left and right actions per se for various frames.
Prerequisites
Must have experience with basic Deep Learning using Tensorflow.
Data source:
Using the cartpole player from OpenAI gym.
(Optional) Suggest/Propose Solutions
I have the solution using Tensorflow, will be happy to create pull request to include the exercise solution.
Learning Goals
Learn the concept of Reinforcement learning by solving the cartpole player problem with the use of OpenAI gym.
Exercise Statement
This exercise helps in learning reinforcement learning using 2 approaches. First, using random playing strategy multiple times and saving parameters for the best average episode. Second, using Deep Q-Learning strategy to optimize the parameters, left and right actions per se for various frames.
Prerequisites
Must have experience with basic Deep Learning using Tensorflow.
Data source:
Using the cartpole player from OpenAI gym.
(Optional) Suggest/Propose Solutions
I have the solution using Tensorflow, will be happy to create pull request to include the exercise solution.