{"id":"https://openalex.org/W2031067035","doi":"https://doi.org/10.1109/devlrn.2014.6982985","title":"Inverse reinforcement learning using Dynamic Policy Programming","display_name":"Inverse reinforcement learning using Dynamic Policy Programming","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2031067035","doi":"https://doi.org/10.1109/devlrn.2014.6982985","mag":"2031067035"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2014.6982985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","raw_type":"proceedings-article"},"type":"article","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/A5031054137","display_name":"Eiji Uchibe","orcid":"https://orcid.org/0000-0001-7908-0258"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Eiji Uchibe","raw_affiliation_strings":["Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-son, Okinawa, Japan","Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, 904-0495, Japan"],"affiliations":[{"raw_affiliation_string":"Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-son, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]},{"raw_affiliation_string":"Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, 904-0495, Japan","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-son, Okinawa, Japan","Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, 904-0495, Japan"],"affiliations":[{"raw_affiliation_string":"Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Onna-son, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]},{"raw_affiliation_string":"Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, 1919-1 Tancha, Onna-son, 904-0495, Japan","institution_ids":["https://openalex.org/I142637625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031054137"],"corresponding_institution_ids":["https://openalex.org/I142637625"],"apc_list":null,"apc_paid":null,"fwci":2.045,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89092074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"228"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.76007479429245},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.7247818112373352},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6905741691589355},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6256961226463318},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6000736951828003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5807071328163147},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5479405522346497},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4846266210079193},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4757504165172577},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.36175310611724854},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3608417809009552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2984234690666199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20259737968444824}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.76007479429245},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7247818112373352},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6905741691589355},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6256961226463318},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6000736951828003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807071328163147},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5479405522346497},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4846266210079193},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4757504165172577},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36175310611724854},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3608417809009552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2984234690666199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20259737968444824},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1109/devlrn.2014.6982985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2014.6982985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Development and Learning and on Epigenetic Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W91088564","https://openalex.org/W1503398984","https://openalex.org/W1559990548","https://openalex.org/W1777239053","https://openalex.org/W1925816294","https://openalex.org/W1994648061","https://openalex.org/W1999874108","https://openalex.org/W2029722408","https://openalex.org/W2061562262","https://openalex.org/W2088042731","https://openalex.org/W2093524643","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2102689555","https://openalex.org/W2107662876","https://openalex.org/W2113501460","https://openalex.org/W2116774898","https://openalex.org/W2119333483","https://openalex.org/W2133068870","https://openalex.org/W2155098712","https://openalex.org/W2155919457","https://openalex.org/W2171302338","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2962901215","https://openalex.org/W3005581722","https://openalex.org/W3022547535","https://openalex.org/W4301630257","https://openalex.org/W6633543754","https://openalex.org/W6638088447","https://openalex.org/W6640290305","https://openalex.org/W6674884181","https://openalex.org/W6675341372","https://openalex.org/W6675547039","https://openalex.org/W6679958247"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2952594763","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2003293420"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,102,106,110],"novel":[4],"model-free":[5],"inverse":[6],"reinforcement":[7],"learning":[8],"method":[9,68,85],"based":[10],"on":[11],"density":[12,53,60],"ratio":[13,29,54,61],"estimation":[14,55],"under":[15],"the":[16,25,28,31,35,41,45,59,65,73,77,82,89,94],"framework":[17],"of":[18,27,62,101],"Dynamic":[19],"Policy":[20],"Programming.":[21],"We":[22],"show":[23],"that":[24,80],"logarithm":[26],"between":[30],"optimal":[32],"policy":[33,37],"and":[34,44,64,76,109],"baseline":[36],"is":[38,50],"represented":[39],"by":[40],"state-dependent":[42,74],"cost":[43,75],"value":[46,78],"function.":[47,96],"Our":[48,84],"proposal":[49],"to":[51,57,71],"use":[52],"methods":[56],"estimate":[58,72],"policies":[63],"least":[66],"squares":[67],"with":[69],"regularization":[70],"function":[79],"satisfies":[81],"relation.":[83],"can":[86],"avoid":[87],"computing":[88],"integral":[90],"such":[91],"as":[92],"evaluating":[93],"partition":[95],"A":[97],"simple":[98],"numerical":[99],"simulation":[100],"grid":[103],"world":[104],"navigation,":[105],"car":[107],"driving,":[108],"pendulum":[111],"swing-up":[112],"shows":[113],"its":[114],"superiority":[115],"over":[116],"conventional":[117],"methods.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}