Skip to content

Custom maze environment used to run and test Reinforcement Learning agents.

Notifications You must be signed in to change notification settings

FMIProjects/RL-Labyrinth

Repository files navigation

RL-Labyrinth

Description

This project consists of a custom maze environment made using the base gym environment and ran using a coupled GUI made using pygame. The purpose is to train and test reinforcement learning agents on this environment.

Features

Procedurally generated maze environment

The maze is generated procedurally and the location of the objectives and agent are also randomized.

Imagine 1 Imagine 2

Tools to build on

The environment can be derived in order to be further customized. This feature is useful to test custom observation spaces of the environment.

Agent creation and training

The project contains APIs that makes agent creation and training easy, as the environment is gym based. Implementations of such agents are SARSA and Q-Learning. The performance was measured for each agent, an example of SARSA would be in the following image:

Usage

  1. Clone the repo
  2. Create Environment via Conda
    conda env create -f environment.yml
    conda activate RL-Labyrinth

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •