{"id":"https://openalex.org/W2211996086","doi":"https://doi.org/10.1109/iros.2015.7353414","title":"Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning","display_name":"Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2211996086","doi":"https://doi.org/10.1109/iros.2015.7353414","mag":"2211996086"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7353414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7353414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5077505054","display_name":"Pravesh Ranchod","orcid":"https://orcid.org/0000-0001-7157-1714"},"institutions":[{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Pravesh Ranchod","raw_affiliation_strings":["University of the Witwatersrand, Johannesburg-Braamfontein, Gauteng, ZA"],"affiliations":[{"raw_affiliation_string":"University of the Witwatersrand, Johannesburg-Braamfontein, Gauteng, ZA","institution_ids":["https://openalex.org/I192619145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068297734","display_name":"Benjamin Rosman","orcid":"https://orcid.org/0000-0002-0284-4114"},"institutions":[{"id":"https://openalex.org/I192619145","display_name":"University of the Witwatersrand","ror":"https://ror.org/03rp50x72","country_code":"ZA","type":"education","lineage":["https://openalex.org/I192619145"]},{"id":"https://openalex.org/I21360634","display_name":"Council for Scientific and Industrial Research","ror":"https://ror.org/05j00sr48","country_code":"ZA","type":"government","lineage":["https://openalex.org/I21360634"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin Rosman","raw_affiliation_strings":["The Council for Scientific and Industrial Research, Pretoria, South Africa","The School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa"],"affiliations":[{"raw_affiliation_string":"The Council for Scientific and Industrial Research, Pretoria, South Africa","institution_ids":["https://openalex.org/I21360634"]},{"raw_affiliation_string":"The School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa","institution_ids":["https://openalex.org/I192619145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078124517","display_name":"George Konidaris","orcid":"https://orcid.org/0000-0002-4460-2519"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Konidaris","raw_affiliation_strings":["The Departments of Computer Science and Electrical and Computer Engineering, Duke University, NC, USA"],"affiliations":[{"raw_affiliation_string":"The Departments of Computer Science and Electrical and Computer Engineering, Duke University, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077505054"],"corresponding_institution_ids":["https://openalex.org/I192619145"],"apc_list":null,"apc_paid":null,"fwci":8.4862,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97575385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.998199999332428,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9836000204086304,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6959385275840759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6655774116516113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6382046341896057},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5866912007331848},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5815857648849487},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5548893213272095},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5012176036834717},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4844701290130615},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.48224076628685},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4771561026573181},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42637336254119873},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2581120729446411},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16774481534957886},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09679332375526428}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6959385275840759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655774116516113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6382046341896057},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5866912007331848},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5815857648849487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5548893213272095},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5012176036834717},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4844701290130615},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.48224076628685},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4771561026573181},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42637336254119873},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2581120729446411},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16774481534957886},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09679332375526428},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2015.7353414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7353414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":38,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W52822972","https://openalex.org/W579399935","https://openalex.org/W1487928270","https://openalex.org/W1515851193","https://openalex.org/W1963873191","https://openalex.org/W1968466370","https://openalex.org/W1975713381","https://openalex.org/W1999874108","https://openalex.org/W2008491003","https://openalex.org/W2022760091","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2105156548","https://openalex.org/W2109910161","https://openalex.org/W2113656889","https://openalex.org/W2117675763","https://openalex.org/W2119914747","https://openalex.org/W2125838338","https://openalex.org/W2127031267","https://openalex.org/W2134491302","https://openalex.org/W2155307968","https://openalex.org/W2162942763","https://openalex.org/W2165300526","https://openalex.org/W2167340365","https://openalex.org/W2167866158","https://openalex.org/W2181849516","https://openalex.org/W2874800706","https://openalex.org/W3098293252","https://openalex.org/W6617022711","https://openalex.org/W6674884181","https://openalex.org/W6677033742","https://openalex.org/W6677555207","https://openalex.org/W6677978604","https://openalex.org/W6678622106","https://openalex.org/W6684258127","https://openalex.org/W6684346986","https://openalex.org/W6685962732"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4312713068"],"abstract_inverted_index":{"We":[0,52,91],"present":[1],"a":[2,6,26,54,78,96,101],"method":[3,76],"for":[4],"segmenting":[5],"set":[7,79],"of":[8,44,80],"unstructured":[9],"demonstration":[10,49],"trajectories":[11],"to":[12,35,58,68,111],"discover":[13],"reusable":[14],"skills":[15,45,114],"using":[16],"inverse":[17,65],"reinforcement":[18,66],"learning":[19,67],"(IRL).":[20],"Each":[21],"skill":[22,39,60],"is":[23,33,109],"characterised":[24],"by":[25],"latent":[27],"reward":[28,70],"function":[29],"which":[30],"the":[31,42,73,88],"demonstrator":[32],"assumed":[34],"be":[36],"optimizing.":[37],"The":[38],"boundaries":[40],"and":[41,62,100],"number":[43],"making":[46],"up":[47],"each":[48],"are":[50],"unknown.":[51],"use":[53],"Bayesian":[55],"nonparametric":[56],"approach":[57,94],"propose":[59],"segmentations":[61],"maximum":[63],"entropy":[64],"infer":[69],"functions":[71],"from":[72],"segments.":[74],"This":[75],"produces":[77],"Markov":[81],"Decision":[82],"Processes":[83],"(MDPs)":[84],"that":[85,107],"best":[86],"describe":[87],"input":[89],"trajectories.":[90],"evaluate":[92],"this":[93],"in":[95],"car":[97],"driving":[98],"domain":[99],"simulated":[102],"quadcopter":[103],"obstacle":[104],"course,":[105],"showing":[106],"it":[108],"able":[110],"recover":[112],"demonstrated":[113],"more":[115],"effectively":[116],"than":[117],"existing":[118],"methods.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6}],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2025-10-10T00:00:00"}