{"id":"https://openalex.org/W3114605215","doi":"https://doi.org/10.1109/icra48506.2021.9561874","title":"Mesh Based Analysis of Low Fractal Dimension Reinforcement Learning Policies","display_name":"Mesh Based Analysis of Low Fractal Dimension Reinforcement Learning Policies","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3114605215","doi":"https://doi.org/10.1109/icra48506.2021.9561874","mag":"3114605215"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.13032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038111090","display_name":"Sean Gillen","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean Gillen","raw_affiliation_strings":["University of California,Electrical and Computer Engineering Department,Santa Barbara,CA,93106","University of California Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California,Electrical and Computer Engineering Department,Santa Barbara,CA,93106","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071708309","display_name":"Katie Byl","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katie Byl","raw_affiliation_strings":["University of California,Electrical and Computer Engineering Department,Santa Barbara,CA,93106","University of California Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California,Electrical and Computer Engineering Department,Santa Barbara,CA,93106","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038111090"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01173486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3546","last_page":"3552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9247999787330627,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.8038451671600342},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7175819873809814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6693867444992065},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.553482174873352},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5449283719062805},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5412669777870178},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4503282308578491},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4496324062347412},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43970999121665955},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4341368079185486},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4149039387702942},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3357546329498291},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25283995270729065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18370741605758667},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14887630939483643}],"concepts":[{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.8038451671600342},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7175819873809814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693867444992065},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.553482174873352},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5449283719062805},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5412669777870178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4503282308578491},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4496324062347412},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43970999121665955},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4341368079185486},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4149039387702942},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3357546329498291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25283995270729065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18370741605758667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14887630939483643},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.13032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.13032","pdf_url":"https://arxiv.org/pdf/2012.13032","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3114605215","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2012.13032.pdf","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.2012.13032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.13032","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.13032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.13032","pdf_url":"https://arxiv.org/pdf/2012.13032","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114605215.pdf","grobid_xml":"https://content.openalex.org/works/W3114605215.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1982880998","https://openalex.org/W2294535740","https://openalex.org/W2726187156","https://openalex.org/W2735039421","https://openalex.org/W2885163910","https://openalex.org/W2890326782","https://openalex.org/W2911087563","https://openalex.org/W2913754617","https://openalex.org/W2929842775","https://openalex.org/W2972420235","https://openalex.org/W3210235935","https://openalex.org/W6697349633","https://openalex.org/W6740222838","https://openalex.org/W6754787993","https://openalex.org/W6758741661","https://openalex.org/W6761206229","https://openalex.org/W6787312507"],"related_works":["https://openalex.org/W3024764221","https://openalex.org/W3048304628","https://openalex.org/W3099303842","https://openalex.org/W3212368910","https://openalex.org/W2951029270","https://openalex.org/W2911722107","https://openalex.org/W23560277","https://openalex.org/W3010257396","https://openalex.org/W2958708366","https://openalex.org/W2739211902","https://openalex.org/W103181800","https://openalex.org/W3202124232","https://openalex.org/W2979435954","https://openalex.org/W3014710427","https://openalex.org/W3110729291","https://openalex.org/W3116610253","https://openalex.org/W2198325613","https://openalex.org/W162145636","https://openalex.org/W1040735863","https://openalex.org/W1570523567"],"abstract_inverted_index":{"In":[0,68,114],"previous":[1,193],"work,":[2,116],"using":[3,195],"a":[4,22,33,54,69,76,87,111,133,176,182],"process":[5],"we":[6,74,117],"call":[7],"meshing,":[8],"the":[9,38,61,65,128,144,151,166,192],"reachable":[10,129,158],"state":[11,130,179],"spaces":[12],"for":[13,40,80],"various":[14],"continuous":[15],"and":[16,138],"hybrid":[17],"systems":[18,209],"were":[19],"approximated":[20],"as":[21,110],"discrete":[23,112],"set":[24],"of":[25,37,64,72,90,122,127,132,174],"states":[26],"which":[27,104],"can":[28,105],"then":[29],"be":[30,106,204],"synthesized":[31],"into":[32],"Markov":[34],"chain.":[35],"One":[36],"applications":[39],"this":[41,115],"approach":[42],"has":[43],"been":[44,219],"to":[45,97,136,181,199,206,211],"analyze":[46,200],"locomotion":[47],"policies":[48,99,141,153,202],"obtained":[49,142],"by":[50,124,140],"reinforcement":[51,82],"learning,":[52],"in":[53],"step":[55],"towards":[56],"making":[57],"empirical":[58],"guarantees":[59],"about":[60],"stability":[62],"properties":[63],"resulting":[66],"system.":[67],"separate":[70],"line":[71],"research,":[73],"introduced":[75],"modified":[77,145,152],"reward":[78,94,169],"function":[79],"on-policy":[81],"learning":[83],"algorithms":[84],"that":[85,100,150,162,191],"utilizes":[86],"\"fractal":[88],"dimension\"":[89],"rollout":[91],"trajectories.":[92],"This":[93,160],"was":[95],"shown":[96],"encourage":[98],"induce":[101],"individual":[102],"trajectories":[103],"more":[107,177],"compactly":[108],"represented":[109],"mesh.":[113],"combine":[118],"these":[119],"two":[120],"threads":[121],"research":[123],"building":[125],"meshes":[126,214],"space":[131,180],"system":[134],"subject":[135],"disturbances":[137],"controlled":[139],"with":[143,165,184],"reward.":[146],"Our":[147],"analysis":[148],"shows":[149,161],"do":[154],"produce":[155],"much":[156],"smaller":[157],"meshes.":[159],"agents":[163],"trained":[164],"fractal":[167],"dimension":[168],"transfer":[170],"their":[171],"desirable":[172],"quality":[173],"having":[175],"compact":[178],"setting":[183],"external":[185],"disturbances.":[186],"The":[187],"results":[188],"also":[189],"suggest":[190],"work":[194],"mesh":[196],"based":[197],"tools":[198],"RL":[201],"may":[203],"extended":[205],"higher":[207,212],"dimensional":[208],"or":[210],"resolution":[213],"than":[215],"would":[216],"have":[217],"otherwise":[218],"possible.":[220]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}