{"id":"https://openalex.org/W2732054432","doi":"https://doi.org/10.1109/devlrn.2012.6400810","title":"What good are actions? Accelerating learning using learned action priors","display_name":"What good are actions? Accelerating learning using learned action priors","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2732054432","doi":"https://doi.org/10.1109/devlrn.2012.6400810","mag":"2732054432"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2012.6400810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068297734","display_name":"Benjamin Rosman","orcid":"https://orcid.org/0000-0002-0284-4114"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Rosman","raw_affiliation_strings":["Institute of Perception, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Perception, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071122608","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["Mobile Intelligent Autonomous Systems (MIAS) CSIR, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Intelligent Autonomous Systems (MIAS) CSIR, South Africa","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.9034441709518433},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7123863697052002},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6843385696411133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6620193123817444},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.586327850818634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769814848899841},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5224303603172302},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4886780083179474},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4604393541812897},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43229299783706665},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4279812276363373},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.25858867168426514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22098895907402039},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.062222808599472046}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.9034441709518433},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7123863697052002},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6843385696411133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620193123817444},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.586327850818634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769814848899841},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5224303603172302},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4886780083179474},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4604393541812897},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43229299783706665},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4279812276363373},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25858867168426514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22098895907402039},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.062222808599472046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/devlrn.2012.6400810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.901.3490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.901.3490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researchspace.csir.co.za/dspace/bitstream/10204/6475/1/Rosman_2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W318964629","https://openalex.org/W1586944634","https://openalex.org/W1598748993","https://openalex.org/W1600813180","https://openalex.org/W1601795611","https://openalex.org/W1612195517","https://openalex.org/W1663973292","https://openalex.org/W1930422559","https://openalex.org/W2034637124","https://openalex.org/W2079247031","https://openalex.org/W2097381042","https://openalex.org/W2098201806","https://openalex.org/W2111868822","https://openalex.org/W2121863487","https://openalex.org/W2149390907","https://openalex.org/W2162147694","https://openalex.org/W2165792602","https://openalex.org/W2166254514","https://openalex.org/W2174706414","https://openalex.org/W2245825236","https://openalex.org/W4214717370","https://openalex.org/W6611072779","https://openalex.org/W6635131279","https://openalex.org/W6635732164","https://openalex.org/W6636553048","https://openalex.org/W6674600207","https://openalex.org/W6683811827","https://openalex.org/W6684428122","https://openalex.org/W6684499351","https://openalex.org/W6690740874"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"The":[0],"computational":[1],"complexity":[2],"of":[3,14,39,51,108,125],"learning":[4,32,126,133],"in":[5,42,58,82,130],"sequential":[6],"decision":[7],"problems":[8],"grows":[9],"exponentially":[10],"with":[11,87,113,127],"the":[12,18,37,59,83,106,123],"number":[13],"actions":[15],"available":[16],"to":[17,66,77,94],"agent":[19],"at":[20],"each":[21,40,43],"state.":[22,44],"We":[23,90],"present":[24],"a":[25,49,131],"method":[26,93],"for":[27,80],"accelerating":[28],"this":[29],"process":[30],"by":[31],"action":[33,41,96,128],"priors":[34,97,110,129],"that":[35],"express":[36],"usefulness":[38],"These":[45],"are":[46,64],"learned":[47],"from":[48,55,70],"set":[50],"different":[52,88],"optimal":[53],"policies":[54],"many":[56],"tasks":[57,81,112],"same":[60,84],"state":[61,115],"space,":[62],"and":[63,117,120],"used":[65],"bias":[67],"exploration":[68],"away":[69],"less":[71],"useful":[72],"actions.":[73],"This":[74],"is":[75],"shown":[76],"improve":[78],"performance":[79],"domain":[85],"but":[86],"goals.":[89],"extend":[91],"our":[92],"base":[95],"on":[98],"perceptual":[99],"cues":[100],"rather":[101],"than":[102],"absolute":[103],"states,":[104],"allowing":[105],"transfer":[107],"these":[109],"between":[111],"differing":[114],"spaces":[116],"transition":[118],"functions,":[119],"demonstrate":[121],"experimentally":[122],"advantages":[124],"reinforcement":[132],"context.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}