File Exchange

image thumbnail

Q-learning (Model-free Value Iteration) Algorithm for Deterministic Cleaning Robot

version 1.0.0.0 (3.98 KB) by Reza Ahmadzadeh
An Example for Reinforcement Learning using Q-learning with epsilon-greedy exploration

13 Downloads

Updated 05 Mar 2014

View License

Q-learning with epsilon-greedy exploration Algorithm for Deterministic Cleaning Robot V1
The deterministic cleaning-robot MDP
a cleaning robot has to collect a used can also has to recharge its
batteries. the state describes the position of the robot and the action
describes the direction of motion. The robot can move to the left or to
the right. The first (1) and the final (6) states are the terminal
states. The goal is to find an optimal policy that maximizes the return
from any initial state. Here the Q-learning epsilon-greedy exploration
algorithm (in Reinforcement learning) is used.
Algorithm 2-3, from:
@book{busoniu2010reinforcement,
title={Reinforcement learning and dynamic programming using function approximators},
author={Busoniu, Lucian and Babuska, Robert and De Schutter, Bart and Ernst, Damien},
year={2010},
publisher={CRC Press}
}

Comments and Ratings (7)

Amir.F

hello.I am trying to run this program but it has debugging. what shoud I do?

Nathan Zhang

Dowoo Kim

Zhang Wei

wonderful example to illustrate model-free value iteration. Looking for demos dealing with system with uncertainty. That will further shows this method's characteristics.

MATLAB Release Compatibility
Created with R2012a
Compatible with any release
Platform Compatibility
Windows macOS Linux