{"id":"https://openalex.org/W3014012509","doi":"https://doi.org/10.1007/978-3-030-73959-1_16","title":"Modelling Agent Policies with Interpretable Imitation Learning","display_name":"Modelling Agent Policies with Interpretable Imitation Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3014012509","doi":"https://doi.org/10.1007/978-3-030-73959-1_16","mag":"3014012509"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-73959-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-73959-1_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.11309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017714952","display_name":"Tom Bewley","orcid":"https://orcid.org/0000-0002-5460-0744"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tom Bewley","raw_affiliation_strings":["University of Bristol, Bristol, UK","University of Bristol"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042150057","display_name":"Jonathan Lawry","orcid":"https://orcid.org/0000-0002-3488-5682"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Lawry","raw_affiliation_strings":["University of Bristol, Bristol, UK","University of Bristol"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058133830","display_name":"Arthur Richards","orcid":"https://orcid.org/0000-0001-9500-5514"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arthur Richards","raw_affiliation_strings":["University of Bristol, Bristol, UK","University of Bristol"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017714952"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3586,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49976863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9908999800682068,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9908999800682068,"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":0.989300012588501,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9761999845504761,"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/imitation","display_name":"Imitation","score":0.7369707226753235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6777292490005493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6354163885116577},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5943698287010193},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5696494579315186},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5638721585273743},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5607008934020996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5034279227256775},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49250397086143494},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45023900270462036},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39052146673202515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10881853103637695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.067970871925354},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0643475353717804}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7369707226753235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777292490005493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6354163885116577},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5943698287010193},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5696494579315186},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5638721585273743},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5607008934020996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5034279227256775},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49250397086143494},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45023900270462036},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39052146673202515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10881853103637695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.067970871925354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0643475353717804},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/978-3-030-73959-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-73959-1_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2006.11309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11309","pdf_url":"https://arxiv.org/pdf/2006.11309","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/525b7111-b322-4a6d-b0d7-a6ed8552c086","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/525b7111-b322-4a6d-b0d7-a6ed8552c086","pdf_url":"https://research-information.bris.ac.uk/en/publications/modelling-agent-policies-with-interpretable-imitation-learning(525b7111-b322-4a6d-b0d7-a6ed8552c086).html","source":{"id":"https://openalex.org/S7407055359","display_name":"Explore Bristol Research","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bewley, T, Lawry, J & Richards, A G 2020, 'Modelling Agent Policies with Interpretable Imitation Learning'. < https://arxiv.org/pdf/2006.11309.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:3014012509","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.11309","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.11309","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.11309","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":null,"raw_type":"article"},{"id":"doi:10.13140/rg.2.2.10343.19366","is_oa":true,"landing_page_url":"https://doi.org/10.13140/rg.2.2.10343.19366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.11309","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11309","pdf_url":"https://arxiv.org/pdf/2006.11309","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1594031697","https://openalex.org/W1828009605","https://openalex.org/W2753415590","https://openalex.org/W2787666871","https://openalex.org/W2994120362","https://openalex.org/W3007111659"],"related_works":["https://openalex.org/W2883057932","https://openalex.org/W3211687843","https://openalex.org/W3000173070","https://openalex.org/W3167487806","https://openalex.org/W3212983817","https://openalex.org/W2293813487","https://openalex.org/W2409817223","https://openalex.org/W3200635221","https://openalex.org/W2322506775","https://openalex.org/W3037793033","https://openalex.org/W2034252760","https://openalex.org/W2074652972","https://openalex.org/W3080365088","https://openalex.org/W2148086733","https://openalex.org/W3098974658","https://openalex.org/W1985742288","https://openalex.org/W2134154552","https://openalex.org/W2292075479","https://openalex.org/W2102690504","https://openalex.org/W2006198267"],"abstract_inverted_index":{"As":[0,47],"we":[1,52],"deploy":[2],"autonomous":[3],"agents":[4],"in":[5,34,41,83],"safety-critical":[6],"domains,":[7],"it":[8],"becomes":[9],"important":[10],"to":[11,25],"develop":[12],"an":[13,23,81],"understanding":[14],"of":[15,44,49,67],"their":[16],"internal":[17],"mechanisms":[18],"and":[19,55],"representations.":[20],"We":[21,75],"outline":[22],"approach":[24],"imitation":[26],"learning":[27],"for":[28],"reverse-engineering":[29],"black":[30],"box":[31],"agent":[32],"policies":[33],"MDP":[35],"environments,":[36],"yielding":[37],"simplified,":[38],"interpretable":[39],"models":[40],"the":[42,72],"form":[43],"decision":[45],"trees.":[46],"part":[48],"this":[50],"process,":[51],"explicitly":[53],"model":[54],"learn":[56],"agents\u2019":[57],"latent":[58],"state":[59],"representations":[60],"by":[61],"selecting":[62],"from":[63,71,80],"a":[64,84],"large":[65],"space":[66],"candidate":[68],"features":[69],"constructed":[70],"Markov":[73],"state.":[74],"present":[76],"initial":[77],"promising":[78],"results":[79],"implementation":[82],"multi-agent":[85],"traffic":[86],"environment.":[87]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}