HQ-learning

Marco Wiering; Jürgen Schmidhuber

doi:10.1177/105971239700600202

HQ-learning

Marco Wiering, Jürgen Schmidhuber

Research output: Contribution to journal › Article › peer-review

133 Scopus citations

Abstract

HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.

Original language	English (US)
Pages (from-to)	219-246
Number of pages	28
Journal	Adaptive Behavior
Volume	6
Issue number	2
DOIs	https://doi.org/10.1177/105971239700600202
State	Published - Jan 1 1997
Externally published	Yes

ASJC Scopus subject areas

Behavioral Neuroscience
Experimental and Cognitive Psychology

Access to Document

10.1177/105971239700600202

Cite this

@article{3df8b8bc0d014323b1879d6899fc9672,

title = "HQ-learning",

abstract = "HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.",

author = "Marco Wiering and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "1997",

month = jan,

day = "1",

doi = "10.1177/105971239700600202",

language = "English (US)",

volume = "6",

pages = "219--246",

journal = "Adaptive Behavior",

issn = "1059-7123",

publisher = "SAGE Publications Ltd",

number = "2",

}

TY - JOUR

T1 - HQ-learning

AU - Wiering, Marco

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 1997/1/1

Y1 - 1997/1/1

N2 - HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.

AB - HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.

UR - http://journals.sagepub.com/doi/10.1177/105971239700600202

UR - http://www.scopus.com/inward/record.url?scp=0031215211&partnerID=8YFLogxK

U2 - 10.1177/105971239700600202

DO - 10.1177/105971239700600202

M3 - Article

SN - 1059-7123

VL - 6

SP - 219

EP - 246

JO - Adaptive Behavior

JF - Adaptive Behavior

IS - 2

ER -

HQ-learning

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this