{"id":"https://openalex.org/W3033650617","doi":null,"title":"Understanding Finite-State Representations of Recurrent Policy Networks","display_name":"Understanding Finite-State Representations of Recurrent Policy Networks","publication_year":2020,"publication_date":"2020-06-06","ids":{"openalex":"https://openalex.org/W3033650617","mag":"3033650617"},"language":"en","primary_location":{"id":"mag:3033650617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.03745.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.03745.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039506832","display_name":"Mohamad H. Danesh","orcid":"https://orcid.org/0000-0003-4182-4930","observed_orcids":["https://orcid.org/0000-0003-4182-4930"]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamad H. Danesh","raw_affiliation_strings":["[OREGON STATE UNIVERSITY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[OREGON STATE UNIVERSITY]","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046705184","display_name":"Anurag Koul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Koul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030052689","display_name":"Alan Fern","orcid":"https://orcid.org/0000-0001-5851-8935","observed_orcids":["https://orcid.org/0000-0001-5851-8935","https://orcid.org/0000-0003-1615-6774"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Fern","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5851-8935","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103005789","display_name":"Saeed Khorram","orcid":"https://orcid.org/0000-0001-7027-0119","observed_orcids":["https://orcid.org/0000-0001-7027-0119"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saeed Khorram","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7027-0119","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8173999786376953,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8173999786376953,"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":0.09610000252723694,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.013899999670684338,"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/finite-state-machines","display_name":"finite automata","score":0.7649999856948853},{"id":"https://openalex.org/keywords/policy-interpretability","display_name":"policy interpretability","score":0.7170000076293945},{"id":"https://openalex.org/keywords/state-minimization","display_name":"state minimization","score":0.7739999890327454},{"id":"https://openalex.org/keywords/state-merging","display_name":"state merging","score":0.734000027179718},{"id":"https://openalex.org/keywords/saliency-analysis","display_name":"saliency analysis","score":0.9160000085830688},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.859000027179718}],"concepts":[{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.6978148818016052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514564156532288},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6000544428825378},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5638571381568909},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5346288681030273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5014188289642334},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4757770597934723},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46628615260124207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36920982599258423},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3451520502567291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13993540406227112},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12988713383674622},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12490612268447876},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07357046008110046},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3033650617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.03745.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3033650617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.03745.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1839273017","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2098467469","https://openalex.org/W2121092017","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2157331557","https://openalex.org/W2163022590","https://openalex.org/W2173564293","https://openalex.org/W2260756217","https://openalex.org/W2434014514","https://openalex.org/W2594633041","https://openalex.org/W2754879180","https://openalex.org/W2770406504","https://openalex.org/W2891830784","https://openalex.org/W2902538158","https://openalex.org/W2907361867","https://openalex.org/W2908064123","https://openalex.org/W2962954781","https://openalex.org/W2970738355","https://openalex.org/W2970909667","https://openalex.org/W2977229822","https://openalex.org/W2995372147","https://openalex.org/W2996457711","https://openalex.org/W3124922852"],"related_works":["https://openalex.org/W3172592753","https://openalex.org/W2902538158","https://openalex.org/W2167378781","https://openalex.org/W2091126994","https://openalex.org/W2972622742","https://openalex.org/W7096322802","https://openalex.org/W2068036649","https://openalex.org/W1976453110","https://openalex.org/W2082345008","https://openalex.org/W2108533559"],"abstract_inverted_index":{"We":[0,59],"introduce":[1],"an":[2,43],"approach":[3,40,94],"for":[4],"understanding":[5,30,69],"finite-state":[6],"machine":[7,45],"(FSM)":[8],"representations":[9],"of":[10,56,70,73],"recurrent":[11],"policy":[12],"networks.":[13],"Recent":[14],"work":[15],"focused":[16],"on":[17,81],"minimizing":[18],"FSMs":[19],"to":[20,65],"gain":[21],"high-level":[22],"insight,":[23],"however,":[24],"minimization":[25],"can":[26,95],"obscure":[27],"a":[28,62,67],"deeper":[29,68],"by":[31],"merging":[32],"states":[33],"that":[34,50,92,98],"are":[35],"semantically":[36],"distinct.":[37],"Conversely,":[38],"our":[39],"starts":[41],"with":[42],"unminimized":[44],"and":[46,87],"applies":[47],"more-interpretable":[48],"reductions":[49],"preserve":[51],"the":[52,57,71,76,93],"key":[53],"decision":[54],"points":[55],"policy.":[58],"also":[60],"contribute":[61],"saliency":[63],"tool":[64],"attain":[66],"role":[72],"observations":[74],"in":[75,103],"decisions.":[77],"Our":[78],"case":[79],"studies":[80],"policies":[82],"from":[83],"7":[84],"Atari":[85],"games":[86],"3":[88],"control":[89],"benchmarks":[90],"demonstrate":[91],"reveal":[96],"insights":[97],"have":[99],"not":[100],"been":[101],"noticed":[102],"prior":[104],"work.":[105]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-06-12T00:00:00"}
