Hamed Shah-Hosseini
  • Home
  • Data Science
    Data Science with Python Data Science with KNIME
  • Learning in AI
    Deep Learning Machine Learning Reinforcement Learning
  • Computer Vision
    Scikit-image OpenCV
  • Robotics
    Autonomous Mobile Robots Multi-robot Systems
  • Optimization
    Mathematical Optimization Swarm Intelligence and Metaheuristics
  • Information Hiding
    Data Hiding Watermarking
  • Computer Graphics
    OpenGL Blender Processing and p5.js
  • About
Part 1 Part 2 Part 3 Q-learning and Cart-pole problem

reinforcement learning under construction

...
...

OpenAI and Gym for cart-pole problem

Here. Installation of the Gym is mentioned. Then, Q-learning is reviewed shortly. Afterwards, all steps are expressed in Python. Moreover, simulations are provided throughout the presentation.