Showing 26 to 30 of 72 posts.

Slider Image

Today I started coding for a solution in mountain climb problem using the Open AI gym library. 

Today I finished coding the Q-learning method using Open AI gym to find the optimal controller.

Today I started writing a code that finds the optimal controller for the Cart-pole problem using a Q-learning algorithm.

Today, I wrote a code that tries to maximize the duration that pole stays in the air before hitting the ground.

Slider Image
February 5th, 2019

Day 42: OpenAI gym library

Today I read about OpenAI gym, a library for reinforcement learning algorithms.