/RL-QLearning

This repository is an implementation of a Reinforcement Learning algorithm called Q-Learning. It solves the Cliff Walking problem defined by Sutton and Barto. It uses Python and the OpenAI Cliff Walking environment.

Primary LanguageJupyter Notebook

Reinforcement Learning - Q-Learning algorithm implementation

This is the code for the Q-Learning algorithm applied to the Cliff Walking problem defined by Sutton & Barto.

The notebook is a kind of guide for studying and understanding the problem solution.