{"id":"https://openalex.org/W4283787033","doi":"https://doi.org/10.1088/2632-2153/ac7ddc","title":"Curiosity in exploring chemical spaces: intrinsic rewards for molecular reinforcement learning","display_name":"Curiosity in exploring chemical spaces: intrinsic rewards for molecular reinforcement learning","publication_year":2022,"publication_date":"2022-07-02","ids":{"openalex":"https://openalex.org/W4283787033","doi":"https://doi.org/10.1088/2632-2153/ac7ddc"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ac7ddc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac7ddc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ac7ddc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031162954","display_name":"Luca Thiede","orcid":"https://orcid.org/0000-0003-1202-6809"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Luca A Thiede","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1202-6809","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022581666","display_name":"Mario Krenn","orcid":"https://orcid.org/0000-0003-1620-9207"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210110240","display_name":"Max Planck Institute for the Science of Light","ror":"https://ror.org/020as7681","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210110240"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA","DE"],"is_corresponding":false,"raw_author_name":"Mario Krenn","raw_affiliation_strings":["Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, University of Toronto, Toronto, Canada","Max Planck Institute for the Science of Light (MPL), Erlangen, Germany","Vector Institute, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1620-9207","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Max Planck Institute for the Science of Light (MPL), Erlangen, Germany","institution_ids":["https://openalex.org/I4210110240"]},{"raw_affiliation_string":"Vector Institute, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029665492","display_name":"AkshatKumar Nigam","orcid":"https://orcid.org/0000-0002-5152-2082"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"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":["CA","US"],"is_corresponding":false,"raw_author_name":"AkshatKumar Nigam","raw_affiliation_strings":["Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, Stanford University, Stanford, CA, United States of America","Department of Computer Science, University of Toronto, Toronto, Canada","Department of Genetics, Stanford University, Stanford, CA, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, United States of America","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Genetics, Stanford University, Stanford, CA, United States of America","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071495561","display_name":"Al\u00e1n Aspuru\u2010Guzik","orcid":"https://orcid.org/0000-0002-8277-4434"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Al\u00e1n Aspuru-Guzik","raw_affiliation_strings":["Department of Chemistry, University of Toronto, Toronto, Canada","Department of Computer Science, University of Toronto, Toronto, Canada","Lebovic Fellow, Canadian Institute for Advanced Research (CIFAR), 661 University Ave, Toronto, Ontario M5G, Canada","Vector Institute, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Lebovic Fellow, Canadian Institute for Advanced Research (CIFAR), 661 University Ave, Toronto, Ontario M5G, Canada","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Vector Institute, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031162954"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":2.4381,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90185192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"3","issue":"3","first_page":"035008","last_page":"035008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9199000000953674,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8561185598373413},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8267295360565186},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.766364336013794},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.6383787989616394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.622199296951294},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5694844126701355},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5514041185379028},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5496094226837158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46674686670303345},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3959490954875946},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3820311427116394},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.2517215311527252},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14808061718940735},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1314832866191864},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09801051020622253},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07569944858551025},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.07229581475257874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06872281432151794}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8561185598373413},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8267295360565186},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.766364336013794},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.6383787989616394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.622199296951294},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5694844126701355},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5514041185379028},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5496094226837158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46674686670303345},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3959490954875946},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3820311427116394},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2517215311527252},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14808061718940735},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1314832866191864},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09801051020622253},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07569944858551025},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.07229581475257874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06872281432151794},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/ac7ddc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac7ddc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2012.11293","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.11293","pdf_url":"https://arxiv.org/pdf/2012.11293","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ac7ddc","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ac7ddc","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2197124934","display_name":null,"funder_award_id":"FR44234","funder_id":"https://openalex.org/F4320322675","funder_display_name":"Mitacs"}],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320321487","display_name":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320334620","display_name":"Natural Resources Canada","ror":"https://ror.org/05hepy730"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1988037271","https://openalex.org/W1988526405","https://openalex.org/W2023818227","https://openalex.org/W2034549041","https://openalex.org/W2034806191","https://openalex.org/W2064675550","https://openalex.org/W2151697120","https://openalex.org/W2153861051","https://openalex.org/W2160592148","https://openalex.org/W2329488992","https://openalex.org/W2529996553","https://openalex.org/W2578240541","https://openalex.org/W2610148085","https://openalex.org/W2618625858","https://openalex.org/W2623491082","https://openalex.org/W2736601468","https://openalex.org/W2786722833","https://openalex.org/W2786785157","https://openalex.org/W2883583109","https://openalex.org/W2885550588","https://openalex.org/W2900694120","https://openalex.org/W2908837618","https://openalex.org/W2914261249","https://openalex.org/W2914542247","https://openalex.org/W2949475445","https://openalex.org/W2953128081","https://openalex.org/W2963276097","https://openalex.org/W2963521729","https://openalex.org/W2963523627","https://openalex.org/W2969456553","https://openalex.org/W2977044154","https://openalex.org/W3009321976","https://openalex.org/W3014154196","https://openalex.org/W3045928028","https://openalex.org/W3046264932","https://openalex.org/W3098269892","https://openalex.org/W3169283615","https://openalex.org/W3170966572","https://openalex.org/W3205976514","https://openalex.org/W4235112493","https://openalex.org/W4240656779","https://openalex.org/W4243270491","https://openalex.org/W4287867830","https://openalex.org/W4294024451","https://openalex.org/W4297796727","https://openalex.org/W6622487243","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6737665993","https://openalex.org/W6738087714","https://openalex.org/W6738599175","https://openalex.org/W6741002519","https://openalex.org/W6747545182","https://openalex.org/W6747927160","https://openalex.org/W6753925943","https://openalex.org/W6766694020","https://openalex.org/W6768561264","https://openalex.org/W6771807793","https://openalex.org/W6796210360","https://openalex.org/W6801860107"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4383268304"],"abstract_inverted_index":{"Abstract":[0],"Computer":[1],"aided":[2,37],"design":[3],"of":[4,13,86,124,145],"molecules":[5,121],"has":[6,150,163],"the":[7,11,63,101,115,141,151],"potential":[8,152],"to":[9,33,75,89,153,156],"disrupt":[10],"field":[12],"drug":[14],"and":[15,20,31,68],"material":[16],"discovery.":[17],"Machine":[18],"learning":[19,22,40,72,136],"deep":[21],"in":[23,28,100,106],"particular,":[24],"made":[25],"big":[26],"strides":[27],"recent":[29],"years":[30],"promises":[32],"greatly":[34],"benefit":[35],"computer":[36],"methods.":[38],"Reinforcement":[39],"is":[41,54,66],"a":[42],"particularly":[43],"promising":[44],"approach":[45],"since":[46],"it":[47],"enables":[48],"de":[49],"novo":[50],"molecule":[51],"design,":[52,56],"that":[53,103,114,138],"molecular":[55,159],"without":[57],"providing":[58],"any":[59,70],"prior":[60],"knowledge.":[61],"However,":[62],"search":[64],"space":[65,143],"vast,":[67],"therefore":[69],"reinforcement":[71,135],"agent":[73],"needs":[74],"perform":[76],"efficient":[77,91],"exploration.":[78,92],"In":[79],"this":[80],"study,":[81],"we":[82],"examine":[83],"three":[84,125],"versions":[85],"intrinsic":[87,98],"motivation":[88,99],"aid":[90],"The":[93],"algorithms":[94],"are":[95],"adapted":[96],"from":[97],"literature":[102],"were":[104],"developed":[105],"other":[107],"settings,":[108],"predominantly":[109],"video":[110],"games.":[111],"We":[112],"show":[113],"curious":[116],"agents":[117,137],"finds":[118],"better":[119],"performing":[120],"on":[122],"two":[123],"benchmarks.":[126],"This":[127,149],"indicates":[128],"an":[129],"exciting":[130],"new":[131,158],"research":[132],"direction":[133],"for":[134],"can":[139],"explore":[140],"chemical":[142],"out":[144],"their":[146],"own":[147],"motivation.":[148],"eventually":[154],"lead":[155],"unexpected":[157],"designs":[160],"no":[161],"human":[162],"thought":[164],"about":[165],"so":[166],"far.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2022-07-04T00:00:00"}