Peter Stone's Selected Publications

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


Transfer Learning for Reinforcement Learning on a Physical Robot

Samuel Barrett, Matt E. Taylor, and Peter Stone. Transfer Learning for Reinforcement Learning on a Physical Robot. In Ninth International Conference on Autonomous Agents and Multiagent Systems - Adaptive Learning Agents Workshop (AAMAS - ALA), May 2010.
AAMAS ALA 2010

Download

[PDF]688.8kB  [postscript]5.7MB  

Abstract

As robots become more widely available, many capabilities that were once only practical to develop and test in simulation are becoming feasible on real, physically grounded, robots. This newfound feasibility is important because simulators rarely represent the world with sufficient fidelity that developed behaviors will work as desired in the real world. However, development and testing on robots remains difficult and time consuming, so it is desirable to minimize the number of trials needed when developing robot behaviors. This paper focuses on reinforcement learning (RL) on physically grounded robots. A few noteworthy exceptions notwithstanding, RL has typically been done purely in simulation, or, at best, initially in simulation with the eventual learned behaviors run on a real robot. However, some recent RL methods exhibit sufficiently low sample complexity to enable learning entirely on robots. One such method is transfer learning for RL. The main contribution of this paper is the first empirical demonstration that transfer learning can significantly speed up and even improve asymptotic performance of RL done entirely on a physical robot. In addition, we show that transferring information learned in simulation can bolster additional learning on the robot.

BibTeX Entry

@InProceedings{AAMASWS10-barrett,
   author = "Samuel Barrett and Matt E.\ Taylor and Peter Stone",
   title = "Transfer Learning for Reinforcement Learning on a Physical Robot",
   booktitle = "Ninth International Conference on Autonomous Agents and Multiagent Systems - Adaptive Learning Agents Workshop (AAMAS - ALA)",
   location = "Toronto, Canada",
   month = "May",
   year = "2010",
   abstract = { 
		As robots become more widely available, many capabilities that were once
		only practical to develop and test in simulation are becoming feasible
		on real, physically grounded, robots.  This newfound feasibility is
		important because simulators rarely represent the world with sufficient
		fidelity that developed behaviors will work as desired in the real 
		world.  However, development and testing on robots remains difficult and
		time consuming, so it is desirable to minimize the number of trials
		needed when developing robot behaviors.
		This paper focuses on reinforcement learning (RL) on physically grounded 
		robots.  A few noteworthy exceptions notwithstanding, RL has typically
		been done purely in simulation, or, at best, initially in simulation
		with the eventual learned behaviors run on a real robot.  However, some
		recent RL methods exhibit sufficiently low sample complexity to enable
		learning entirely on robots.  One such method is transfer learning for
		RL.  The main contribution of this paper is the first empirical 
		demonstration that transfer learning can significantly speed up and even
		improve asymptotic performance of RL done entirely on a physical robot.
		In addition, we show that transferring information learned in simulation
		can bolster additional learning on the robot.
	},
   wwwnote={<a href="http://www-users.cs.york.ac.uk/~kudenko/ala10/">AAMAS ALA 2010</a>},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 05, 2014 13:23:04