---
abstract: 'Action Selection schemes, when translated into precise algorithms, typically involve considerable design effort and tuning of parameters. Little work has been done on solving the problem using learning. This paper compares eight different methods of solving the action selection problem using Reinforcement Learning (learning from rewards). The methods range from centralised and cooperative to decentralised and selfish. They are tested in an artificial world and their performance, memory requirements and reactiveness are compared. Finally, the possibility of more exotic, ecosystem-like decentralised models are considered.'
altloc:
- http://www.ed.ac.uk/~humphrys/Publications/g.SAB96.ps.gz
chapter: ~
commentary: ~
commref: ~
confdates: 1996
conference: 'From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior'
confloc: 'Massachusetts, USA'
contact_email: ~
creators_id: []
creators_name:
- family: Humphrys
given: Mark
honourific: ''
lineage: ''
date: 1996
date_type: published
datestamp: 1998-06-09
department: ~
dir: disk0/00/00/04/47
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name:
- family: Maes
given: Pattie
honourific: ''
lineage: ''
- family: Mataric
given: Maja
honourific: ''
lineage: ''
- family: Meyer
given: Jean-Arcady
honourific: ''
lineage: ''
- family: Pollack
given: Jordan
honourific: ''
lineage: ''
- family: Wilson
given: Stewart W.
honourific: ''
lineage: ''
eprint_status: archive
eprintid: 447
fileinfo: /style/images/fileicons/application_postscript.png;/447/2/g.SAB96.ps
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: ~
lastmod: 2011-03-11 08:53:57
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: 135-144
pubdom: FALSE
publication: ~
publisher: MIT Press/Bradford Books
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 10
series: ~
source: ~
status_changed: 2007-09-12 16:28:04
subjects:
- bio-ani-behav
- bio-etho
- comp-sci-art-intel
- comp-sci-mach-dynam-sys
- comp-sci-mach-learn
- comp-sci-robot
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: Action Selection methods using Reinforcement Learning
type: confpaper
userid: 69
volume: ~