{"id":"https://openalex.org/W4232512588","doi":"https://doi.org/10.1109/cdc.2014.7040156","title":"Infinite time horizon maximum causal entropy inverse reinforcement learning","display_name":"Infinite time horizon maximum causal entropy inverse reinforcement learning","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W4232512588","doi":"https://doi.org/10.1109/cdc.2014.7040156"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7040156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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/A5068955929","display_name":"Michael Bloem","orcid":"https://orcid.org/0000-0001-5864-7753"},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bloem","raw_affiliation_strings":["Aviation Systems Division, NASA Ames Research Center, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aviation Systems Division, NASA Ames Research Center, CA, USA","institution_ids":["https://openalex.org/I1280536761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002056995","display_name":"Nicholas Bambos","orcid":"https://orcid.org/0000-0001-9250-4553"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Bambos","raw_affiliation_strings":["Departments of Electrical Engineering and Management Science & Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Electrical Engineering and Management Science & Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0206,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.91016548,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4911","last_page":"4916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12617","display_name":"Energy, Environment, and Transportation Policies","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9714000225067139,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9667999744415283,"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":0.7952841520309448},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6538268327713013},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6256853938102722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5834659934043884},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5356454849243164},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4567701518535614},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4299643337726593},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32440823316574097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2790699899196625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21693113446235657},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21049293875694275}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7952841520309448},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6538268327713013},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6256853938102722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834659934043884},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5356454849243164},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4567701518535614},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4299643337726593},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32440823316574097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2790699899196625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21693113446235657},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21049293875694275},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2014.7040156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7040156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.5621","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.5621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aviationsystemsdivision.arc.nasa.gov/publications/2015/IEEE-CDC2014_Bloem.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1489262227","https://openalex.org/W1999874108","https://openalex.org/W2051944318","https://openalex.org/W2069855531","https://openalex.org/W2070406545","https://openalex.org/W2098432798","https://openalex.org/W2140834544","https://openalex.org/W2142477416","https://openalex.org/W2147544021","https://openalex.org/W2321545103","https://openalex.org/W4250589301","https://openalex.org/W6629237864","https://openalex.org/W6681478256","https://openalex.org/W6903351479","https://openalex.org/W7066018963"],"related_works":["https://openalex.org/W2049472152","https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4389475841","https://openalex.org/W2152670157","https://openalex.org/W2903299703","https://openalex.org/W4281791088","https://openalex.org/W2117282672","https://openalex.org/W4385342861","https://openalex.org/W1574958246"],"abstract_inverted_index":{"We":[0,157],"extend":[1,124],"the":[2,12,70,101,110,114,120,140],"maximum":[3],"causal":[4,28],"entropy":[5,29],"framework":[6],"for":[7,95],"inverse":[8],"reinforcement":[9,130],"learning":[10,131],"to":[11,27,31,50,69,167],"infinite":[13],"time":[14],"horizon":[15],"discounted":[16,24,33],"reward":[17],"setting.":[18],"To":[19],"do":[20],"so,":[21],"we":[22,123,143],"maximize":[23],"future":[25],"contributions":[26],"subject":[30],"a":[32,75,80,86,96,106,168,175],"feature":[34],"expectation":[35],"matching":[36],"constraint.":[37],"A":[38],"parameterized":[39],"class":[40],"of":[41,62,79,82,85,161],"stochastic":[42],"policies":[43,54],"that":[44,64,92,133],"solve":[45,94],"this":[46,162],"problem":[47,169],"are":[48],"referred":[49],"as":[51],"soft":[52,97,116,136],"Bellman":[53,71,98,117,137],"because":[55],"they":[56,134],"can":[57,144],"be":[58],"specified":[59],"in":[60,184],"terms":[61],"values":[63],"satisfy":[65],"an":[66],"equation":[67,72],"identical":[68],"but":[73],"with":[74],"softmax":[76],"(the":[77],"log":[78],"sum":[81],"exponentials)":[83],"instead":[84],"max.":[87],"Under":[88],"some":[89],"assumptions,":[90],"algorithms":[91,160],"repeatedly":[93],"policy,":[99,102],"evaluate":[100],"and":[103,129],"then":[104],"perform":[105,153],"gradient":[107],"update":[108],"on":[109],"parameters":[111],"will":[112],"find":[113],"optimal":[115],"policy.":[118],"For":[119,139],"first":[121],"step,":[122,142],"techniques":[125,148],"from":[126,149,174],"dynamic":[127,150],"programming":[128,151],"so":[132],"derive":[135],"policies.":[138],"second":[141],"use":[145],"policy":[146],"evaluation":[147],"or":[152],"Monte":[154],"Carlo":[155],"simulations.":[156],"compare":[158],"three":[159],"type":[163],"by":[164,182],"applying":[165],"them":[166],"instance":[170],"involving":[171],"demonstration":[172],"data":[173],"simple":[176],"controlled":[177],"queuing":[178],"network":[179],"model":[180],"inspired":[181],"problems":[183],"air":[185],"traffic":[186],"management.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}