An architecture for adaptive intelligent systems:
Abstract: "Our goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by 'adaptive intelligent systems (AISs).' In contrast with niches occupied by typical AI agents, AIS niches...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Stanford, Calif.
1993
|
| Schriftenreihe: | Stanford University / Computer Science Department: Report STAN CS
1496 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "Our goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by 'adaptive intelligent systems (AISs).' In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper To function effectively throughout the range of situations presented by an AIS niche, an agent must be highly adaptive. In contrast with the rather stereotypic behavior of typical AI agents, an AIS must adapt several key aspects of its behavior to its dynamic situation: its perceptual strategy, its control mode, its choices of reasoning tasks to perform, its choices of reasoning methods for performing chosen tasks; and its meta-control strategy for global coordination of all its behavior. We have designed and implemented an agent architecture that supports all of these different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors The architecture has been used to build experimental agents for several AIS niches. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring. |
| Beschreibung: | 49 S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV009568017 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 940427s1993 |||| 00||| eng d | ||
| 035 | |a (OCoLC)30464386 | ||
| 035 | |a (DE-599)BVBBV009568017 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-29T | ||
| 100 | 1 | |a Hayes-Roth, Barbara |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a An architecture for adaptive intelligent systems |c Barbara Hayes-Roth |
| 246 | 1 | 3 | |a Reportnr.: KSL 93 19 |
| 264 | 1 | |a Stanford, Calif. |c 1993 | |
| 300 | |a 49 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Stanford University / Computer Science Department: Report STAN CS |v 1496 | |
| 520 | 3 | |a Abstract: "Our goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by 'adaptive intelligent systems (AISs).' In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper | |
| 520 | 3 | |a To function effectively throughout the range of situations presented by an AIS niche, an agent must be highly adaptive. In contrast with the rather stereotypic behavior of typical AI agents, an AIS must adapt several key aspects of its behavior to its dynamic situation: its perceptual strategy, its control mode, its choices of reasoning tasks to perform, its choices of reasoning methods for performing chosen tasks; and its meta-control strategy for global coordination of all its behavior. We have designed and implemented an agent architecture that supports all of these different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors | |
| 520 | 3 | |a The architecture has been used to build experimental agents for several AIS niches. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring. | |
| 650 | 4 | |a Künstliche Intelligenz | |
| 650 | 4 | |a Artificial intelligence | |
| 810 | 2 | |a Computer Science Department: Report STAN CS |t Stanford University |v 1496 |w (DE-604)BV008928280 |9 1496 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-006321076 | ||
Datensatz im Suchindex
| _version_ | 1804123908096393216 |
|---|---|
| any_adam_object | |
| author | Hayes-Roth, Barbara |
| author_facet | Hayes-Roth, Barbara |
| author_role | aut |
| author_sort | Hayes-Roth, Barbara |
| author_variant | b h r bhr |
| building | Verbundindex |
| bvnumber | BV009568017 |
| ctrlnum | (OCoLC)30464386 (DE-599)BVBBV009568017 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02789nam a2200337 cb4500</leader><controlfield tag="001">BV009568017</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940427s1993 |||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)30464386</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV009568017</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-29T</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hayes-Roth, Barbara</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An architecture for adaptive intelligent systems</subfield><subfield code="c">Barbara Hayes-Roth</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">Reportnr.: KSL 93 19</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Stanford, Calif.</subfield><subfield code="c">1993</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">49 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">Stanford University / Computer Science Department: Report STAN CS</subfield><subfield code="v">1496</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Our goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by 'adaptive intelligent systems (AISs).' In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">To function effectively throughout the range of situations presented by an AIS niche, an agent must be highly adaptive. In contrast with the rather stereotypic behavior of typical AI agents, an AIS must adapt several key aspects of its behavior to its dynamic situation: its perceptual strategy, its control mode, its choices of reasoning tasks to perform, its choices of reasoning methods for performing chosen tasks; and its meta-control strategy for global coordination of all its behavior. We have designed and implemented an agent architecture that supports all of these different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The architecture has been used to build experimental agents for several AIS niches. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Künstliche Intelligenz</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Computer Science Department: Report STAN CS</subfield><subfield code="t">Stanford University</subfield><subfield code="v">1496</subfield><subfield code="w">(DE-604)BV008928280</subfield><subfield code="9">1496</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006321076</subfield></datafield></record></collection> |
| id | DE-604.BV009568017 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:37:14Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-006321076 |
| oclc_num | 30464386 |
| open_access_boolean | |
| owner | DE-29T |
| owner_facet | DE-29T |
| physical | 49 S. |
| publishDate | 1993 |
| publishDateSearch | 1993 |
| publishDateSort | 1993 |
| record_format | marc |
| series2 | Stanford University / Computer Science Department: Report STAN CS |
| spelling | Hayes-Roth, Barbara Verfasser aut An architecture for adaptive intelligent systems Barbara Hayes-Roth Reportnr.: KSL 93 19 Stanford, Calif. 1993 49 S. txt rdacontent n rdamedia nc rdacarrier Stanford University / Computer Science Department: Report STAN CS 1496 Abstract: "Our goal is to understand and build comprehensive agents that function effectively in challenging niches. In particular, we identify a class of niches to be occupied by 'adaptive intelligent systems (AISs).' In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper To function effectively throughout the range of situations presented by an AIS niche, an agent must be highly adaptive. In contrast with the rather stereotypic behavior of typical AI agents, an AIS must adapt several key aspects of its behavior to its dynamic situation: its perceptual strategy, its control mode, its choices of reasoning tasks to perform, its choices of reasoning methods for performing chosen tasks; and its meta-control strategy for global coordination of all its behavior. We have designed and implemented an agent architecture that supports all of these different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors The architecture has been used to build experimental agents for several AIS niches. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring. Künstliche Intelligenz Artificial intelligence Computer Science Department: Report STAN CS Stanford University 1496 (DE-604)BV008928280 1496 |
| spellingShingle | Hayes-Roth, Barbara An architecture for adaptive intelligent systems Künstliche Intelligenz Artificial intelligence |
| title | An architecture for adaptive intelligent systems |
| title_alt | Reportnr.: KSL 93 19 |
| title_auth | An architecture for adaptive intelligent systems |
| title_exact_search | An architecture for adaptive intelligent systems |
| title_full | An architecture for adaptive intelligent systems Barbara Hayes-Roth |
| title_fullStr | An architecture for adaptive intelligent systems Barbara Hayes-Roth |
| title_full_unstemmed | An architecture for adaptive intelligent systems Barbara Hayes-Roth |
| title_short | An architecture for adaptive intelligent systems |
| title_sort | an architecture for adaptive intelligent systems |
| topic | Künstliche Intelligenz Artificial intelligence |
| topic_facet | Künstliche Intelligenz Artificial intelligence |
| volume_link | (DE-604)BV008928280 |
| work_keys_str_mv | AT hayesrothbarbara anarchitectureforadaptiveintelligentsystems AT hayesrothbarbara reportnrksl9319 |