Connectionist environment modelling in a real robot:
Abstract: "This paper describes some experiments with an adaptive controller, based on multi-layer perceptrons, which tries to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readin...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Buch |
Sprache: | English |
Veröffentlicht: |
Edinburgh
1994
|
Schriftenreihe: | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper
673 |
Schlagworte: | |
Zusammenfassung: | Abstract: "This paper describes some experiments with an adaptive controller, based on multi-layer perceptrons, which tries to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readings will change if it performs a given action; another learns, with the aid of the model, to evaluate sensory states according to how close the robot is to receiving a reward when it expriences them. Two kinds of model which exploit context information were evaluated in robot runs, as well as a 'flat' (memoryless) model. The results confirm that backprop can provide the learning mechanism needed to solve simple adaptive control tasks, and point up some problems which will need to be addressed before it can help with more complicated skills." |
Beschreibung: | [11] S. |
Internformat
MARC
LEADER | 00000nam a2200000 cb4500 | ||
---|---|---|---|
001 | BV010466524 | ||
003 | DE-604 | ||
005 | 00000000000000.0 | ||
007 | t | ||
008 | 951108s1994 |||| 00||| engod | ||
035 | |a (OCoLC)32841285 | ||
035 | |a (DE-599)BVBBV010466524 | ||
040 | |a DE-604 |b ger |e rakddb | ||
041 | 0 | |a eng | |
049 | |a DE-91G | ||
100 | 1 | |a Chesters, William |e Verfasser |4 aut | |
245 | 1 | 0 | |a Connectionist environment modelling in a real robot |c William Chesters and Gillian Hayes |
264 | 1 | |a Edinburgh |c 1994 | |
300 | |a [11] S. | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
490 | 1 | |a University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |v 673 | |
520 | 3 | |a Abstract: "This paper describes some experiments with an adaptive controller, based on multi-layer perceptrons, which tries to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readings will change if it performs a given action; another learns, with the aid of the model, to evaluate sensory states according to how close the robot is to receiving a reward when it expriences them. Two kinds of model which exploit context information were evaluated in robot runs, as well as a 'flat' (memoryless) model. The results confirm that backprop can provide the learning mechanism needed to solve simple adaptive control tasks, and point up some problems which will need to be addressed before it can help with more complicated skills." | |
650 | 7 | |a Bionics and artificial intelligence |2 sigle | |
650 | 7 | |a Robotics and its application |2 sigle | |
650 | 4 | |a Neural networks (Computer science) | |
700 | 1 | |a Hayes, Gillian |e Verfasser |4 aut | |
810 | 2 | |a Department of Artificial Intelligence: DAI research paper |t University <Edinburgh> |v 673 |w (DE-604)BV010450646 |9 673 | |
999 | |a oai:aleph.bib-bvb.de:BVB01-006974496 |
Datensatz im Suchindex
_version_ | 1804124899441115136 |
---|---|
any_adam_object | |
author | Chesters, William Hayes, Gillian |
author_facet | Chesters, William Hayes, Gillian |
author_role | aut aut |
author_sort | Chesters, William |
author_variant | w c wc g h gh |
building | Verbundindex |
bvnumber | BV010466524 |
ctrlnum | (OCoLC)32841285 (DE-599)BVBBV010466524 |
format | Book |
fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01954nam a2200325 cb4500</leader><controlfield tag="001">BV010466524</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">951108s1994 |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)32841285</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV010466524</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91G</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chesters, William</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Connectionist environment modelling in a real robot</subfield><subfield code="c">William Chesters and Gillian Hayes</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Edinburgh</subfield><subfield code="c">1994</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">[11] S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">University <Edinburgh> / Department of Artificial Intelligence: DAI research paper</subfield><subfield code="v">673</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "This paper describes some experiments with an adaptive controller, based on multi-layer perceptrons, which tries to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readings will change if it performs a given action; another learns, with the aid of the model, to evaluate sensory states according to how close the robot is to receiving a reward when it expriences them. Two kinds of model which exploit context information were evaluated in robot runs, as well as a 'flat' (memoryless) model. The results confirm that backprop can provide the learning mechanism needed to solve simple adaptive control tasks, and point up some problems which will need to be addressed before it can help with more complicated skills."</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bionics and artificial intelligence</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Robotics and its application</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Neural networks (Computer science)</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hayes, Gillian</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Artificial Intelligence: DAI research paper</subfield><subfield code="t">University <Edinburgh></subfield><subfield code="v">673</subfield><subfield code="w">(DE-604)BV010450646</subfield><subfield code="9">673</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006974496</subfield></datafield></record></collection> |
id | DE-604.BV010466524 |
illustrated | Not Illustrated |
indexdate | 2024-07-09T17:53:00Z |
institution | BVB |
language | English |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-006974496 |
oclc_num | 32841285 |
open_access_boolean | |
owner | DE-91G DE-BY-TUM |
owner_facet | DE-91G DE-BY-TUM |
physical | [11] S. |
publishDate | 1994 |
publishDateSearch | 1994 |
publishDateSort | 1994 |
record_format | marc |
series2 | University <Edinburgh> / Department of Artificial Intelligence: DAI research paper |
spelling | Chesters, William Verfasser aut Connectionist environment modelling in a real robot William Chesters and Gillian Hayes Edinburgh 1994 [11] S. txt rdacontent n rdamedia nc rdacarrier University <Edinburgh> / Department of Artificial Intelligence: DAI research paper 673 Abstract: "This paper describes some experiments with an adaptive controller, based on multi-layer perceptrons, which tries to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readings will change if it performs a given action; another learns, with the aid of the model, to evaluate sensory states according to how close the robot is to receiving a reward when it expriences them. Two kinds of model which exploit context information were evaluated in robot runs, as well as a 'flat' (memoryless) model. The results confirm that backprop can provide the learning mechanism needed to solve simple adaptive control tasks, and point up some problems which will need to be addressed before it can help with more complicated skills." Bionics and artificial intelligence sigle Robotics and its application sigle Neural networks (Computer science) Hayes, Gillian Verfasser aut Department of Artificial Intelligence: DAI research paper University <Edinburgh> 673 (DE-604)BV010450646 673 |
spellingShingle | Chesters, William Hayes, Gillian Connectionist environment modelling in a real robot Bionics and artificial intelligence sigle Robotics and its application sigle Neural networks (Computer science) |
title | Connectionist environment modelling in a real robot |
title_auth | Connectionist environment modelling in a real robot |
title_exact_search | Connectionist environment modelling in a real robot |
title_full | Connectionist environment modelling in a real robot William Chesters and Gillian Hayes |
title_fullStr | Connectionist environment modelling in a real robot William Chesters and Gillian Hayes |
title_full_unstemmed | Connectionist environment modelling in a real robot William Chesters and Gillian Hayes |
title_short | Connectionist environment modelling in a real robot |
title_sort | connectionist environment modelling in a real robot |
topic | Bionics and artificial intelligence sigle Robotics and its application sigle Neural networks (Computer science) |
topic_facet | Bionics and artificial intelligence Robotics and its application Neural networks (Computer science) |
volume_link | (DE-604)BV010450646 |
work_keys_str_mv | AT chesterswilliam connectionistenvironmentmodellinginarealrobot AT hayesgillian connectionistenvironmentmodellinginarealrobot |