Sciweavers

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

10

ATAL
2010
Springer

favoriteEmaildiscussreport

181views Intelligent Agents» more ATAL 2010»

Basis function construction for hierarchical reinforcement learning

13 years 5 months ago

Basis function construction for hierarchical reinforcement learning

Download www.cs.brown.edu

This paper introduces an approach to automatic basis function construction for Hierarchical Reinforcement Learning (HRL) tasks. We describe some considerations that arise when constructing basis functions for multilevel task hierarchies. We extend previous work on using Laplacian bases for value function approximation to situations where the agent is provided with a multi-level action hierarchy. We experimentally evaluate these techniques on the Taxi domain.

Sarah Osentoski, Sridhar Mahadevan

Real-time Traffic

ATAL 2010 | Basis Function Construction | Basis Functions | Intelligent Agents | Multilevel Task Hierarchies |

claim paper

Related Content

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

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

» Constructing action set from basis functions for reinforcement learning of robot control

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

» The MAXQ Method for Hierarchical Reinforcement Learning

» Hierarchical reinforcement learning with subpolicies specializing for learned subgoals

» A Dynamic Allocation Method of Basis Functions in Reinforcement Learning

» Value Function Approximation in Reinforcement Learning Using the Fourier Basis

» State Space Reduction For Hierarchical Reinforcement Learning

Post Info
More Details (n/a)

Added	08 Nov 2010
Updated	08 Nov 2010
Type	Conference
Year	2010
Where	ATAL
Authors	Sarah Osentoski, Sridhar Mahadevan

Comments (0)