neural networks research group
areas
people
projects
demos
publications
software/data
Critical Factors in the Empirical Performance of Temporal Difference and Evolutionary Methods for Reinforcement Learning (2009)
Shimon Whiteson
and
Matthew E. Taylor
and
Peter Stone
Temporal difference and evolutionary methods are two of the most common approaches to solving reinforcement learning problems. However, there is little consensus on their relative merits and there have been few empirical studies that directly compare their performance. This article aims to address this shortcoming by presenting results of empirical comparisons between Sarsa and NEAT, two representative methods, in mountain car and keepaway, two benchmark reinforcement learning tasks. In each task, the methods are evaluated in combination with both linear and nonlinear representations to determine their best configurations. In addition, this article tests two specific hypotheses about the critical factors contributing to these methods' relative performance: 1) that sensor noise reduces the final performance of Sarsa more than that of NEAT, because Sarsa's learning updates are not reliable in the absence of the Markov property and 2) that stochasticity, by introducing noise in fitness estimates, reduces the learning speed of NEAT more than that of Sarsa. Experiments in variations of mountain car and keepaway designed to isolate these factors confirm both these hypotheses.
View:
PDF
,
PS
,
HTML
Citation:
Journal of Autonomous Agents and Multi-Agent Systems
, 21(1):1-27, 2009.
Bibtex:
@Article{JAAMAS09-Whiteson, title={Critical Factors in the Empirical Performance of Temporal Difference and Evolutionary Methods for Reinforcement Learning}, author={Shimon Whiteson and Matthew E. Taylor and Peter Stone}, volume={21}, journal={Journal of Autonomous Agents and Multi-Agent Systems}, number={1}, pages={1-27}, url="http://nn.cs.utexas.edu/?whiteson:jaamas09", year={2009} }
People
Peter Stone
pstone [at] cs utexas edu
Matthew Taylor
taylorm [at] eecs wsu edu
Shimon Whiteson
Former Collaborator
s a whiteson [at] uva nl
Areas of Interest
Reinforcement Learning