{"id":"https://openalex.org/W4290802777","doi":"https://doi.org/10.48550/arxiv.2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","display_name":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W4290802777","doi":"https://doi.org/10.48550/arxiv.2208.04919"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.04919","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.04919","pdf_url":"https://arxiv.org/pdf/2208.04919","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.04919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084881611","display_name":"Marwa Abdulhai","orcid":"https://orcid.org/0009-0005-2760-559X","observed_orcids":["https://orcid.org/0009-0005-2760-559X"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdulhai, Marwa","raw_affiliation_strings":["Department of Computer Science , University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046953322","display_name":"Natasha Jaques","orcid":"https://orcid.org/0000-0002-8413-9469","observed_orcids":["https://orcid.org/0000-0002-8413-9469"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaques, Natasha","raw_affiliation_strings":["Google Research , Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research , Brain Team","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Levine, Sergey","raw_affiliation_strings":["Department of Computer Science , University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/reward-function-inference","display_name":"reward function inference","score":0.8980000019073486},{"id":"https://openalex.org/keywords/successor-features","display_name":"successor features","score":0.722000002861023},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.7170000076293945},{"id":"https://openalex.org/keywords/multi-task-pre-training","display_name":"multi-task pre-training","score":0.7379999756813049},{"id":"https://openalex.org/keywords/intent-inference","display_name":"intention inference","score":0.6079999804496765},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.6240000128746033}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7816073298454285},{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.7332315444946289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153653502464294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6334744691848755},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6095393896102905},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.53741055727005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5367995500564575},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.523522138595581},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4107426702976227},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0936804711818695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07714194059371948},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.04919","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.04919","pdf_url":"https://arxiv.org/pdf/2208.04919","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2208.04919","doi":"https://doi.org/10.48550/arxiv.2208.04919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.04919","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.04919","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.04919","pdf_url":"https://arxiv.org/pdf/2208.04919","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2473542051","https://openalex.org/W3123320268","https://openalex.org/W2994519609","https://openalex.org/W2726593096","https://openalex.org/W2054269721","https://openalex.org/W4235459050","https://openalex.org/W2767501615","https://openalex.org/W2390822611","https://openalex.org/W2908217413","https://openalex.org/W2158654672"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,12,37,92,125,146,156],"problem":[4],"of":[5,15,39,127],"inverse":[6],"reinforcement":[7,74],"learning":[8,75,83],"(IRL)":[9],"--":[10],"inferring":[11,36,169,176],"reward":[13,60,157,173,177],"function":[14],"an":[16,66,114],"agent":[17,115,147],"from":[18,102,179],"observing":[19],"its":[20,149],"behavior.":[21,68],"IRL":[22,55,93],"can":[23,62,78],"provide":[24,48],"a":[25,40,118,131,138,143],"generalizable":[26],"and":[27,33,87,109,153,170],"compact":[28],"representation":[29],"for":[30,49,121],"apprenticeship":[31],"learning,":[32],"enable":[34],"accurately":[35,175],"preferences":[38,85],"human":[41],"in":[42,130],"order":[43],"to":[44,81,112,116,136,151],"assist":[45],"them.":[46],"%and":[47],"more":[50,88],"accurate":[51],"prediction.":[52],"However,":[53],"effective":[54,167],"is":[56,165],"challenging,":[57],"because":[58],"many":[59],"functions":[61,178],"be":[63,79],"compatible":[64],"with":[65],"observed":[67],"We":[69,90],"focus":[70],"on":[71],"how":[72],"prior":[73],"(RL)":[76],"experience":[77],"leveraged":[80],"make":[82],"these":[84],"faster":[86],"efficient.":[89],"propose":[91],"algorithm":[94],"BASIS":[95],"(Behavior":[96],"Acquisition":[97],"through":[98],"Successor-feature":[99],"Intention":[100],"inference":[101],"Samples),":[103],"which":[104],"leverages":[105],"multi-task":[106],"RL":[107],"pre-training":[108],"successor":[110],"features":[111],"allow":[113],"build":[117],"strong":[119],"basis":[120,150],"intentions":[122],"that":[123,162],"spans":[124],"space":[126],"possible":[128],"goals":[129],"given":[132],"domain.":[133],"When":[134],"exposed":[135],"just":[137],"few":[139],"expert":[140],"demonstrations":[141],"optimizing":[142,171],"novel":[144],"goal,":[145],"uses":[148],"quickly":[152],"effectively":[154],"infer":[155],"function.":[158],"Our":[159],"experiments":[160],"reveal":[161],"our":[163],"method":[164],"highly":[166],"at":[168],"demonstrated":[172],"functions,":[174],"less":[180],"than":[181],"100":[182],"trajectories.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-08-12T00:00:00"}