{"id":"https://openalex.org/W2964306693","doi":"https://doi.org/10.3233/978-1-61499-672-9-1690","title":"Shaping Proto-Value Functions Using Rewards","display_name":"Shaping Proto-Value Functions Using Rewards","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2964306693","doi":"https://doi.org/10.3233/978-1-61499-672-9-1690","mag":"2964306693"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-672-9-1690","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1690","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1511.08589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083450236","display_name":"Raj Kumar Maity","orcid":"https://orcid.org/0000-0002-4759-696X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maity Raj Kumar","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst Center, United States"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst Center, United States","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044247596","display_name":"Chandrashekar Lakshminarayanan","orcid":"https://orcid.org/0000-0002-3570-7175"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lakshminarayanan Chandrashekar","raw_affiliation_strings":["Indian Institute of Science Bangalore, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040002468","display_name":"Sindhu Padakandla","orcid":"https://orcid.org/0000-0003-3385-294X"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Padakandla Sindhu","raw_affiliation_strings":["Indian Institute of Science Bangalore, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038163398","display_name":"Shalabh Bhatnagar","orcid":"https://orcid.org/0000-0001-7644-3914"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhatnagar Shalabh","raw_affiliation_strings":["Indian Institute of Science Bangalore, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083450236"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28099721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1690","last_page":"1691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9988999962806702,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.61409592628479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3603740930557251},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05469745397567749}],"concepts":[{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.61409592628479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3603740930557251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05469745397567749}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-672-9-1690","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1690","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:eprints.iisc.ac.in:55371","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},{"id":"mag:2964306693","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1511.08589","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2964306693","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1511.08589","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W115446000","https://openalex.org/W1544439040","https://openalex.org/W1573527757","https://openalex.org/W1576452626","https://openalex.org/W1597303641","https://openalex.org/W1777239053","https://openalex.org/W1993704541","https://openalex.org/W1998172110","https://openalex.org/W2002305926","https://openalex.org/W2032378315","https://openalex.org/W2060248504","https://openalex.org/W2079247031","https://openalex.org/W2094387729","https://openalex.org/W2098432798","https://openalex.org/W2106261932","https://openalex.org/W2111316871","https://openalex.org/W2113953866","https://openalex.org/W2116810533","https://openalex.org/W2119567691","https://openalex.org/W2120157426","https://openalex.org/W2143958939","https://openalex.org/W2151283311","https://openalex.org/W2155027007","https://openalex.org/W2159880874","https://openalex.org/W2161795906","https://openalex.org/W2164637474","https://openalex.org/W2187770737","https://openalex.org/W3106238320","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,114],"reinforcement":[1],"learning":[2,8,160],"(RL),":[3],"an":[4,45,63],"important":[5],"sub-problem":[6],"is":[7,13,24,90,164],"the":[9,17,52,56,84,111,128,131,136,141,155],"value":[10,22,73,112,156],"function,":[11],"which":[12,104],"chiefly":[14],"influenced":[15],"by":[16],"architecture":[18],"used":[19],"to":[20,51,91,95,139],"represent":[21],"functions.":[23,37],"often":[25],"expressed":[26],"as":[27],"a":[28,32,69,87,93,107,119],"linear":[29],"combination":[30],"of":[31,35,72,130],"pre-selected":[33],"set":[34],"basis":[36,39,60,97,122],"These":[38],"functions":[40,61,77,98],"are":[41,49,100],"either":[42],"selected":[43],"in":[44,62],"ad-hoc":[46,64],"manner":[47,65],"or":[48],"tailored":[50],"RL":[53],"task":[54,101],"using":[55,78],"domain":[57,79],"knowledge.":[58],"Selecting":[59],"does":[66],"not":[67],"give":[68],"good":[70,108,152],"approximation":[71,109,153],"function":[74,123,157],"while":[75],"choosing":[76],"knowledge":[80],"introduces":[81],"dependency":[82],"on":[83,168],"task.":[85],"Thus,":[86],"desirable":[88],"scenario":[89],"have":[92],"method":[94,125],"choose":[96],"that":[99,126],"independent,":[102],"but":[103],"also":[105],"provide":[106],"for":[110,154],"function.":[113],"this":[115],"paper,":[116],"we":[117,149],"propose":[118,150],"novel":[120],"task-independent":[121],"construction":[124],"uses":[127],"topology":[129],"underlying":[132],"state":[133],"space":[134],"and":[135,158],"reward":[137],"structure":[138],"build":[140],"reward-based":[142],"Proto":[143],"Value":[144],"Functions":[145],"(RPVFs).":[146],"The":[147,162],"approach":[148],"gives":[151],"enhanced":[159],"performance.":[161],"performance":[163],"demonstrated":[165],"via":[166],"experiments":[167],"grid-world":[169],"tasks.":[170]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-07-30T00:00:00"}