/RL-Basics

Primary LanguageJupyter Notebook

Reinforcement Learning Basics

In this repository, OpenAI Gym has been used to implement basic RL algorithms.

Implemented algorithms are:

a) DP based policy iteration b) DP based value iteration c) Q-learning

The variations of results with respect to different parameters is also studied.

Author

Abhineet Pandey - abhineet99 - homepage

Acknowledgements

Dr. Shashi Shekhar Jha - For giving this as an assignment under CS529- Applied AI course, Fall 2019.