{"id":"https://openalex.org/W4301895924","doi":"https://doi.org/10.21428/594757db.8e09102d","title":"Balancing Information with Observation Costs in Deep Reinforcement Learning","display_name":"Balancing Information with Observation Costs in Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4301895924","doi":"https://doi.org/10.21428/594757db.8e09102d"},"language":"en","primary_location":{"id":"doi:10.21428/594757db.8e09102d","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.8e09102d","pdf_url":"https://caiac.pubpub.org/pub/0jmy7gpd/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://caiac.pubpub.org/pub/0jmy7gpd/download/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033365772","display_name":"Colin Bellinger","orcid":"https://orcid.org/0000-0002-3567-7834"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Colin Bellinger","raw_affiliation_strings":["Vector Institute for Artificial Intelligence, Toronto, Canada","\u22c4 University of Waterloo, Waterloo, Canada","National Research Council of Canada Ottawa, Canada"],"affiliations":[{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]},{"raw_affiliation_string":"\u22c4 University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"National Research Council of Canada Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091559394","display_name":"Andriy Drozdyuk","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andriy Drozdyuk","raw_affiliation_strings":["\u22c4 University of Waterloo, Waterloo, Canada","National Research Council of Canada Ottawa, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"\u22c4 University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"National Research Council of Canada Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064795613","display_name":"Mark Crowley","orcid":"https://orcid.org/0000-0003-3921-4762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Crowley","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029833367","display_name":"Isaac Tamblyn","orcid":"https://orcid.org/0000-0002-8146-6667"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Isaac Tamblyn","raw_affiliation_strings":["\u22c4 University of Waterloo, Waterloo, Canada","National Research Council of Canada Ottawa, Canada","Vector Institute for Artificial Intelligence, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"\u22c4 University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"National Research Council of Canada Ottawa, Canada","institution_ids":["https://openalex.org/I4210159778"]},{"raw_affiliation_string":"Vector Institute for Artificial Intelligence, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033365772"],"corresponding_institution_ids":["https://openalex.org/I151746483","https://openalex.org/I4210127509","https://openalex.org/I4210159778"],"apc_list":null,"apc_paid":null,"fwci":0.3692,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57840713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9325000047683716,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10409","display_name":"Fuel Cells and Related Materials","score":0.9325000047683716,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10260","display_name":"Software Engineering Research","score":0.8999999761581421,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8690343499183655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278811931610107},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5943132638931274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818018317222595},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5803601741790771},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5470840930938721},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.47366318106651306},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4462319314479828},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.32087117433547974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14813658595085144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08730953931808472},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08496168255805969}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8690343499183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278811931610107},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5943132638931274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818018317222595},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5803601741790771},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5470840930938721},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.47366318106651306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4462319314479828},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.32087117433547974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14813658595085144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08730953931808472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08496168255805969},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21428/594757db.8e09102d","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.8e09102d","pdf_url":"https://caiac.pubpub.org/pub/0jmy7gpd/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:2e701a0c-744b-4c24-b5ce-b8191023ca33","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=2e701a0c-744b-4c24-b5ce-b8191023ca33","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=2e701a0c-744b-4c24-b5ce-b8191023ca33","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.21428/594757db.8e09102d","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.8e09102d","pdf_url":"https://caiac.pubpub.org/pub/0jmy7gpd/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4301895924.pdf","grobid_xml":"https://content.openalex.org/works/W4301895924.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1583953806","https://openalex.org/W2010780110","https://openalex.org/W2032100464","https://openalex.org/W2039170454","https://openalex.org/W2121092017","https://openalex.org/W2134802714","https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2173564293","https://openalex.org/W2607713949","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2790698955","https://openalex.org/W2902762889","https://openalex.org/W2908064123","https://openalex.org/W2950065518","https://openalex.org/W2950906090","https://openalex.org/W2951799221","https://openalex.org/W3028818653","https://openalex.org/W3042021489","https://openalex.org/W3102103141","https://openalex.org/W3106073154","https://openalex.org/W3132960064","https://openalex.org/W3174896399","https://openalex.org/W3183892796","https://openalex.org/W3211465897","https://openalex.org/W4394666657","https://openalex.org/W6737069938","https://openalex.org/W6741002519","https://openalex.org/W6745620495","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,29,65,99,121],"reinforcement":[3],"learning":[4,43],"(RL)":[5],"in":[6,23,38,62,162],"scientific":[7,39,180],"applications,":[8,40],"such":[9],"as":[10],"materials":[11],"design":[12],"and":[13,35,69,90,135,151],"automated":[14],"chemistry,":[15],"is":[16,32],"increasing.":[17],"A":[18],"major":[19],"challenge,":[20],"however,":[21],"lies":[22],"fact":[24],"that":[25,76,126],"measuring":[26],"the":[27,30,58,63,71,97,100,109,114,119,132,166,173],"state":[28,98,149],"system":[31,101],"often":[33],"costly":[34],"time":[36,51,104],"consuming":[37],"whereas":[41],"policy":[42,85],"with":[44,73,118],"RL":[45,80,177],"requires":[46],"a":[47,66,84,157],"measurement":[48,59],"after":[49],"each":[50,103],"step.":[52,105],"In":[53,106],"this":[54,107,130],"work,":[55],"we":[56],"make":[57],"costs":[60,74],"explicit":[61],"form":[64],"costed":[67],"reward":[68],"propose":[70],"active-measure":[72],"framework":[75],"enables":[77],"off-the-shelf":[78],"deep":[79],"algorithms":[81],"to":[82,95,112,146,171,175,178],"learn":[83,111,139],"for":[86,116],"both":[87],"selecting":[88],"actions":[89],"determining":[91],"whether":[92],"or":[93],"not":[94],"measure":[96],"at":[102],"way,":[108],"agents":[110,137],"balance":[113],"need":[115],"information":[117],"cost":[120],"information.":[122],"Our":[123],"results":[124],"show":[125],"when":[127],"trained":[128],"under":[129],"regime,":[131],"Dueling":[133],"DQN":[134],"PPO":[136],"can":[138,155,169],"optimal":[140],"action":[141],"policies":[142],"whilst":[143],"making":[144],"up":[145],"50\\%":[147,160],"fewer":[148],"measurements,":[150],"recurrent":[152],"neural":[153],"networks":[154],"produce":[156],"greater":[158],"than":[159],"reduction":[161,168],"measurements.":[163],"We":[164],"postulate":[165],"these":[167],"help":[170],"lower":[172],"barrier":[174],"applying":[176],"real-world":[179],"applications.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}