Rapid Task Learning for Real Robots View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1993

AUTHORS

Jonathan H. Connell , Sridhar Mahadevan

ABSTRACT

For learning to be useful on real robots, whatever algorithm is used must converge in some “reasonable” amount of time. If each trial step takes on the order of seconds, a million steps would take several months of continuous run time. In many cases such extended runs are neither desirable nor practical. In this chapter we discuss how learning can be speeded up by exploiting properties of the task, sensor configuration, environment, and existing control structure. More... »

PAGES

105-139

Book

TITLE

Robot Learning

ISBN

978-1-4613-6396-5
978-1-4615-3184-5

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4615-3184-5_5

DOI

http://dx.doi.org/10.1007/978-1-4615-3184-5_5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1038118425


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "name": [
            "T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY\u00a010598, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Connell", 
        "givenName": "Jonathan H.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY\u00a010598, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mahadevan", 
        "givenName": "Sridhar", 
        "type": "Person"
      }
    ], 
    "datePublished": "1993", 
    "datePublishedReg": "1993-01-01", 
    "description": "For learning to be useful on real robots, whatever algorithm is used must converge in some \u201creasonable\u201d amount of time. If each trial step takes on the order of seconds, a million steps would take several months of continuous run time. In many cases such extended runs are neither desirable nor practical. In this chapter we discuss how learning can be speeded up by exploiting properties of the task, sensor configuration, environment, and existing control structure.", 
    "editor": [
      {
        "familyName": "Connell", 
        "givenName": "Jonathan H.", 
        "type": "Person"
      }, 
      {
        "familyName": "Mahadevan", 
        "givenName": "Sridhar", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-1-4615-3184-5_5", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-1-4613-6396-5", 
        "978-1-4615-3184-5"
      ], 
      "name": "Robot Learning", 
      "type": "Book"
    }, 
    "name": "Rapid Task Learning for Real Robots", 
    "pagination": "105-139", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4615-3184-5_5"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "b595ede6dc3d06a00050c006b7806c3ea47dd2a5a9fc071f6c360e4843266395"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1038118425"
        ]
      }
    ], 
    "publisher": {
      "location": "Boston, MA", 
      "name": "Springer US", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4615-3184-5_5", 
      "https://app.dimensions.ai/details/publication/pub.1038118425"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T16:05", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8675_00000065.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-1-4615-3184-5_5"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-3184-5_5'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-3184-5_5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-3184-5_5'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4615-3184-5_5'


 

This table displays all metadata directly associated to this object as RDF triples.

76 TRIPLES      22 PREDICATES      27 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4615-3184-5_5 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N253c733b6aec4adebebafac83352dc95
4 schema:datePublished 1993
5 schema:datePublishedReg 1993-01-01
6 schema:description For learning to be useful on real robots, whatever algorithm is used must converge in some “reasonable” amount of time. If each trial step takes on the order of seconds, a million steps would take several months of continuous run time. In many cases such extended runs are neither desirable nor practical. In this chapter we discuss how learning can be speeded up by exploiting properties of the task, sensor configuration, environment, and existing control structure.
7 schema:editor N316b1e36e6464ff09aa41fd846892d4d
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N0b8463cc3ef54e9da58982161b45992a
12 schema:name Rapid Task Learning for Real Robots
13 schema:pagination 105-139
14 schema:productId N0b63492e5a204cc1839d680efb382f01
15 N1a7e5dec439040a1aa111d75d8d6a02e
16 Nce7467596a534d23ab6dd06adfe07553
17 schema:publisher Nd827d769a3de4b5b86e8ae9227729c7d
18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038118425
19 https://doi.org/10.1007/978-1-4615-3184-5_5
20 schema:sdDatePublished 2019-04-15T16:05
21 schema:sdLicense https://scigraph.springernature.com/explorer/license/
22 schema:sdPublisher N3a0b1e37fab9482c8f9990ea5d602df1
23 schema:url http://link.springer.com/10.1007/978-1-4615-3184-5_5
24 sgo:license sg:explorer/license/
25 sgo:sdDataset chapters
26 rdf:type schema:Chapter
27 N0b63492e5a204cc1839d680efb382f01 schema:name doi
28 schema:value 10.1007/978-1-4615-3184-5_5
29 rdf:type schema:PropertyValue
30 N0b8463cc3ef54e9da58982161b45992a schema:isbn 978-1-4613-6396-5
31 978-1-4615-3184-5
32 schema:name Robot Learning
33 rdf:type schema:Book
34 N192adf9a3b964dc4a5f07c639d164c6a schema:familyName Connell
35 schema:givenName Jonathan H.
36 rdf:type schema:Person
37 N1a5c0488d65d45a2aaf758ccf05b42ed schema:familyName Mahadevan
38 schema:givenName Sridhar
39 rdf:type schema:Person
40 N1a7e5dec439040a1aa111d75d8d6a02e schema:name readcube_id
41 schema:value b595ede6dc3d06a00050c006b7806c3ea47dd2a5a9fc071f6c360e4843266395
42 rdf:type schema:PropertyValue
43 N253c733b6aec4adebebafac83352dc95 rdf:first N4240b17f1d4b442b858dd943b2e0399e
44 rdf:rest N3dbd298fed854186b4bfa4447b43bdfc
45 N316b1e36e6464ff09aa41fd846892d4d rdf:first N192adf9a3b964dc4a5f07c639d164c6a
46 rdf:rest Nca35a99930444ceaa498f2ad52457ee5
47 N3a0b1e37fab9482c8f9990ea5d602df1 schema:name Springer Nature - SN SciGraph project
48 rdf:type schema:Organization
49 N3dbd298fed854186b4bfa4447b43bdfc rdf:first Nbca1afb7e21e47088b56a083476b9e1d
50 rdf:rest rdf:nil
51 N4240b17f1d4b442b858dd943b2e0399e schema:affiliation Nc8d1a3a6a84540bbae9a8f5adf6459f0
52 schema:familyName Connell
53 schema:givenName Jonathan H.
54 rdf:type schema:Person
55 N98441964c79d450c808b7b4f1fb848f5 schema:name T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY 10598, USA
56 rdf:type schema:Organization
57 Nbca1afb7e21e47088b56a083476b9e1d schema:affiliation N98441964c79d450c808b7b4f1fb848f5
58 schema:familyName Mahadevan
59 schema:givenName Sridhar
60 rdf:type schema:Person
61 Nc8d1a3a6a84540bbae9a8f5adf6459f0 schema:name T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY 10598, USA
62 rdf:type schema:Organization
63 Nca35a99930444ceaa498f2ad52457ee5 rdf:first N1a5c0488d65d45a2aaf758ccf05b42ed
64 rdf:rest rdf:nil
65 Nce7467596a534d23ab6dd06adfe07553 schema:name dimensions_id
66 schema:value pub.1038118425
67 rdf:type schema:PropertyValue
68 Nd827d769a3de4b5b86e8ae9227729c7d schema:location Boston, MA
69 schema:name Springer US
70 rdf:type schema:Organisation
71 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
72 schema:name Information and Computing Sciences
73 rdf:type schema:DefinedTerm
74 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
75 schema:name Artificial Intelligence and Image Processing
76 rdf:type schema:DefinedTerm
 




Preview window. Press ESC to close (or click here)


...