Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


The Open-Source TEXPLORE Code Release for Reinforcement Learning on Robots

Todd Hester and Peter Stone. The Open-Source TEXPLORE Code Release for Reinforcement Learning on Robots. In Sven Behnke, Arnoud Visser, Rong Xiong, and Manuela Veloso, editors, RoboCup-2013: Robot Soccer World Cup XVII, Lecture Notes in Artificial Intelligence, Springer Verlag, Berlin, 2013.

Download

[PDF]234.7kB  [postscript]2.9MB  

Abstract

The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations on-line. RL is a paradigm for learning sequential decision making tasks, usually formulated as a Markov Decision Process (MDP). For an RL algorithm to be practical for robotic control tasks, it must learn in very few samples, while continually taking actions in real-time. In addition, the algorithm must learn efficiently in the face of noise, sensor/actuator delays, and continuous state features. In this paper, we present the TEXPLORE ROS code release, which contains TEXPLORE, the first algorithm to address all of these challenges together. We demonstrate TEXPLORE learning to control the velocity of an autonomous vehicle in real-time. TEXPLORE has been released as an open-source ROS repository, enabling learning on a variety of robot tasks.

BibTeX Entry

@incollection{RoboCup13-hester,
  author = {Todd Hester and Peter Stone},
  title = {The Open-Source TEXPLORE Code Release for Reinforcement Learning on Robots},
  booktitle= "RoboCup-2013: Robot Soccer World Cup {XVII}",
  Editor={Sven Behnke and Arnoud Visser and Rong Xiong and Manuela Veloso},
  Publisher="Springer Verlag",
  address="Berlin",
  year="2013",
  series="Lecture Notes in Artificial Intelligence",
  abstract= {
   The use of robots in society could be expanded by using reinforcement
   learning (RL) to allow robots to learn and adapt to new situations on-line.
   RL is a paradigm for learning sequential decision making tasks, usually
   formulated as a Markov Decision Process (MDP). For an RL algorithm to be
   practical for robotic control tasks, it must learn in very few samples,
   while continually taking actions in real-time. In addition, the algorithm
   must learn efficiently in the face of noise, sensor/actuator delays, and
   continuous state features. In this paper, we present the TEXPLORE ROS code
   release, which contains TEXPLORE, the first algorithm to address all of
   these challenges together. We demonstrate TEXPLORE learning to control the
   velocity of an autonomous vehicle in real-time. TEXPLORE has been released
   as an open-source ROS repository, enabling learning on a variety of robot
   tasks.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Sep 24, 2014 22:15:11