Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

19

AAAI
2011

favoriteEmaildiscussreport

202views Intelligent Agents» more AAAI 2011»

Value Function Approximation in Reinforcement Learning Using the Fourier Basis

12 years 4 months ago

Value Function Approximation in Reinforcement Learning Using the Fourier Basis

Download people.csail.mit.edu

We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs well compared to Radial Basis Functions and the Polynomial Basis, the two most popular ﬁxed bases for linear value function approximation, and is competitive with learned Proto-Value Functions even though no extra experience or computation is required.

George Konidaris, Sarah Osentoski, Philip Thomas

Real-time Traffic

AAAI 2011 | Approximation Scheme | Intelligent Agents | Polynomial Basis | Radial Basis Functions |

claim paper

Related Content

» Multilayer Perceptrons with Radial Basis Functions as Value Functions in Reinforcement Lea...

» Automatic basis function construction for approximate dynamic programming and reinforcemen...

» Basis Function Construction in Reinforcement Learning Using CascadeCorrelation Learning Ar...

» Basis function construction for hierarchical reinforcement learning

» Protovalue functions developmental reinforcement learning

» Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning

» Value Function Approximation on NonLinear Manifolds for Robot Motor Control

» Asymmetric Multiagent Reinforcement Learning

» Constructing basis functions from directed graphs for value function approximation

Post Info
More Details (n/a)

Added	12 Dec 2011
Updated	12 Dec 2011
Type	Journal
Year	2011
Where	AAAI
Authors	George Konidaris, Sarah Osentoski, Philip Thomas

Comments (0)