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 N873c58662ec149aa954f6e98129e919c
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 N1c7d87727b3c40d893479db9499970d5
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Nd27b62eb9fa9493980d0b7ee86db9656
12 schema:name Rapid Task Learning for Real Robots
13 schema:pagination 105-139
14 schema:productId N3d5801822146494fbd8ff7f8c788583c
15 N7904baa3ffd744dc90658245ef0e7370
16 Nbbea1c96868e4b0caaefb7c2016abefa
17 schema:publisher Ne34c4dd8ee3045d9929463c9e07d4ced
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 N96e69e64e2df482e926cb16e8adaf235
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 N18ea2e136d424ab89a3f778c508b3d17 schema:familyName Connell
28 schema:givenName Jonathan H.
29 rdf:type schema:Person
30 N1bd71e155c7744f9bf124810c191f954 schema:name T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY 10598, USA
31 rdf:type schema:Organization
32 N1c7d87727b3c40d893479db9499970d5 rdf:first N18ea2e136d424ab89a3f778c508b3d17
33 rdf:rest N50bc41a936334c87b3f424d3db7ba641
34 N3d5801822146494fbd8ff7f8c788583c schema:name doi
35 schema:value 10.1007/978-1-4615-3184-5_5
36 rdf:type schema:PropertyValue
37 N41794cc5f68243cba15615bac92e884b schema:affiliation Nd03b36a29f744839bf168e0cd5b41045
38 schema:familyName Connell
39 schema:givenName Jonathan H.
40 rdf:type schema:Person
41 N50bc41a936334c87b3f424d3db7ba641 rdf:first N6b85b83e4fc4442ea992b831f38cbf56
42 rdf:rest rdf:nil
43 N6b85b83e4fc4442ea992b831f38cbf56 schema:familyName Mahadevan
44 schema:givenName Sridhar
45 rdf:type schema:Person
46 N7904baa3ffd744dc90658245ef0e7370 schema:name dimensions_id
47 schema:value pub.1038118425
48 rdf:type schema:PropertyValue
49 N83a88ce09a8e4a0ba101471227822c37 schema:affiliation N1bd71e155c7744f9bf124810c191f954
50 schema:familyName Mahadevan
51 schema:givenName Sridhar
52 rdf:type schema:Person
53 N873c58662ec149aa954f6e98129e919c rdf:first N41794cc5f68243cba15615bac92e884b
54 rdf:rest Nae75a20ce0cd42aa9d6f5da4c0e348e0
55 N96e69e64e2df482e926cb16e8adaf235 schema:name Springer Nature - SN SciGraph project
56 rdf:type schema:Organization
57 Nae75a20ce0cd42aa9d6f5da4c0e348e0 rdf:first N83a88ce09a8e4a0ba101471227822c37
58 rdf:rest rdf:nil
59 Nbbea1c96868e4b0caaefb7c2016abefa schema:name readcube_id
60 schema:value b595ede6dc3d06a00050c006b7806c3ea47dd2a5a9fc071f6c360e4843266395
61 rdf:type schema:PropertyValue
62 Nd03b36a29f744839bf168e0cd5b41045 schema:name T. J. Watson Research Center, IBM, Box 704, Yorktown Heights, NY 10598, USA
63 rdf:type schema:Organization
64 Nd27b62eb9fa9493980d0b7ee86db9656 schema:isbn 978-1-4613-6396-5
65 978-1-4615-3184-5
66 schema:name Robot Learning
67 rdf:type schema:Book
68 Ne34c4dd8ee3045d9929463c9e07d4ced 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)


...