Sciweavers

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

32

ECML
2004
Springer

favoriteEmaildiscussreport

157views Machine Learning» more ECML 2004»

Model Approximation for HEXQ Hierarchical Reinforcement Learning

14 years 4 months ago

Model Approximation for HEXQ Hierarchical Reinforcement Learning

Download www.cse.unsw.edu.au

HEXQ is a reinforcement learning algorithm that discovers hierarchical structure automatically. The generated task hierarchy repthe problem at diﬀerent levels of abstraction. In this paper we extend HEXQ with heuristics that automatically approximate the structure of the task hierarchy. Construction, learning and execution time, as well as storage requirements of a task hierarchy may be signiﬁcantly reduced and traded oﬀ against solution quality.

Bernhard Hengst

Real-time Traffic

ECML 2004 | Generated Task Hierarchy | Reinforcement Learning Algorithm | Task Hierarchy |

claim paper

Related Content

» Discovering Hierarchy in Reinforcement Learning with HEXQ

» Compositional Models for Reinforcement Learning

» Basis function construction for hierarchical reinforcement learning

» Reinforcement Learning Hierarchical NeuroFuzzy Politree Model for Control of Autonomous Ag...

» Hierarchical Reinforcement Learning and Hidden Markov Models for TaskOriented Natural Lang...

» A hierarchical approach to efficient reinforcement learning in deterministic domains

» Hierarchical Reinforcement Learning for Adaptive Text Generation

» Evaluation of a hierarchical reinforcement learning spoken dialogue system

» Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning

Post Info
More Details (n/a)

Added	01 Jul 2010
Updated	01 Jul 2010
Type	Conference
Year	2004
Where	ECML
Authors	Bernhard Hengst

Comments (0)