Skip to content

This github contains a simple OpenAi Gym Maze Enviroment and (at now) a RL Algorithm to solve it.

Notifications You must be signed in to change notification settings

lucadivit/Reinforcement_Learning_Maze_Solver

Repository files navigation

Reinforcement_Learning_Maze_Solver

This github contains a simple OpenAi Gym Maze Enviroment and some RL Algorithms to solve it.

General Info

At now i implemented Q-Learning and Sarsa tabular algorithms, greedy, epsilon greedy, Boltzmann and Boltzmann e greedy policies, and a maze enviroment with OpenAI Gym template.