Fuzzy Rule Interpolation-based Reinforcement Learning

This is the repository of the Final Semester Undergraduation Project on Reinforcement Learning (Inverted Pendulum problem) done by Nikhil Podila and Savinay Nagendra. The project was performed under the guidance of Professor Koshy George at the Center of Intelligent Systems in PES Institute of Technology, Bangalore, India

Pole Balancer is a Python program that uses reinforcement learning (RL) to automatically design a policy for the classic controls problem of a cart balancing a pole. Through Markov decision processes framework, we can perform reinforcement learning without having any explicit knowledge of the physics of the underlying system, in our case, the po…

CartPole problem with reinforcement learning. 10,000 parallel games without rendering

Fuzzy Rule Interpolation-based Reinforcement Learning (C + AVX port)

Experiments on Reinforcement Learning with OpenAI Gyms

Python implementation of the Q Learning algorithm with the DDQN trick on OpenAI's version of the cart-pole problem

Self Balancing AI using Q-Learning