Package net.pakl.rl.maze

World and policy for a 2D problem with impassable obstacles.

See:
Description

Class Summary

Action2D	This class represents a one-dimensional action, which could correspond to a movement vector in a 2D World such as MazeWorld
MazeMain	Allows a command-line based reinforcement learning simulation based on the contents of a maze.prop properties file (see Details below for more information on maze.prop
MazeMainSimple	Simple example to navigate through a grid world for for tutorial/intro purposes; does not load anything from a file but is instead fully self-contained.
MazeWizard
MazeWizardFrame
MazeWorld	This is a model of a 2D gridworld and supports all the functions specified in the World interface.
State2D	This class represents a state which corresponds to a position in a two-dimensional World
Toolbox	The Toolbox is a collection of miscellanious functions to help with initialization of various objects at the beginning of a simulation.

Package net.pakl.rl.maze Description

World and policy for a 2D problem with impassable obstacles.