{"id":"https://openalex.org/W3154691419","doi":"https://doi.org/10.1109/cog52621.2021.9619008","title":"Honey. I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","display_name":"Honey. I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3154691419","doi":"https://doi.org/10.1109/cog52621.2021.9619008","mag":"3154691419"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619008","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038185726","display_name":"Siddharth Mysore","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siddharth Mysore","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,U.S.A","Department of Computer Science, Boston University, Boston, U.S.A"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,U.S.A","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Computer Science, Boston University, Boston, U.S.A","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043815062","display_name":"Bassel El Mabsout","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bassel El Mabsout","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,U.S.A","Department of Computer Science, Boston University, Boston, U.S.A"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,U.S.A","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Computer Science, Boston University, Boston, U.S.A","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035353750","display_name":"Renato Mancuso","orcid":"https://orcid.org/0000-0003-3558-5216"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renato Mancuso","raw_affiliation_strings":["Boston University,Department of Computer Science,Boston,U.S.A","Department of Computer Science, Boston University, Boston, U.S.A"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Computer Science,Boston,U.S.A","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Department of Computer Science, Boston University, Boston, U.S.A","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kate Saenko","raw_affiliation_strings":["Boston University Co-affiliated with MIT-IBM Watson AI Lab,Department of Computer Science,Boston,U.S.A","Department of Computer Science, Boston University Co-affiliated with MIT-IBM Watson AI Lab, Boston, U.S.A"],"affiliations":[{"raw_affiliation_string":"Boston University Co-affiliated with MIT-IBM Watson AI Lab,Department of Computer Science,Boston,U.S.A","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Boston University Co-affiliated with MIT-IBM Watson AI Lab, Boston, U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038185726"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.5074,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64494361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9621000289916992,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9593999981880188,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7177056670188904},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6947067379951477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6828290820121765},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5626285076141357},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4400753676891327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41602954268455505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1959000527858734}],"concepts":[{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7177056670188904},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6947067379951477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828290820121765},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5626285076141357},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4400753676891327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41602954268455505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1959000527858734},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog52621.2021.9619008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619008","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:null:2144/44917","is_oa":false,"landing_page_url":"https://openreview.net/forum?id=Ah8wG7a-3ti","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5042538287","display_name":null,"funder_award_id":"1724237","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1771410628","https://openalex.org/W1821462560","https://openalex.org/W2155027007","https://openalex.org/W2342662072","https://openalex.org/W2736601468","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2766614170","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2797527950","https://openalex.org/W2809668646","https://openalex.org/W2889987506","https://openalex.org/W2949608212","https://openalex.org/W2952746978","https://openalex.org/W2954444343","https://openalex.org/W2963120839","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964043796","https://openalex.org/W2964198579","https://openalex.org/W2964299589","https://openalex.org/W2980810656","https://openalex.org/W2982316857","https://openalex.org/W2995617888","https://openalex.org/W2995894173","https://openalex.org/W2996037775","https://openalex.org/W3013688454","https://openalex.org/W3029466658","https://openalex.org/W3042532592","https://openalex.org/W3092954297","https://openalex.org/W3102089800","https://openalex.org/W3103503471","https://openalex.org/W3114616228","https://openalex.org/W3120947768","https://openalex.org/W3187808158","https://openalex.org/W4287637675","https://openalex.org/W4289303873","https://openalex.org/W4300081896","https://openalex.org/W6638018090","https://openalex.org/W6638523607","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6732837357","https://openalex.org/W6733877748","https://openalex.org/W6742945991","https://openalex.org/W6744123322","https://openalex.org/W6745744936","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6750629867","https://openalex.org/W6752431149","https://openalex.org/W6753526802","https://openalex.org/W6771730547","https://openalex.org/W6772005887","https://openalex.org/W6772196467","https://openalex.org/W6780608970","https://openalex.org/W6784458062","https://openalex.org/W6788186211"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Actors":[0],"and":[1,32,106],"critics":[2,107],"in":[3,66,93,120],"actor-critic":[4,81,111],"reinforcement":[5],"learning":[6],"algorithms":[7,82],"are":[8,108],"functionally":[9],"separate,":[10],"yet":[11],"they":[12],"often":[13,45],"use":[14],"the":[15,23,38,67],"same":[16],"network":[17,27,70],"architectures.":[18],"This":[19],"case":[20],"study":[21],"explores":[22],"performance":[24,54],"impact":[25],"of":[26,40,69,76,97,104,110],"sizes":[28],"when":[29,124],"considering":[30],"actor":[31,90],"critic":[33],"architectures":[34],"independently.":[35],"By":[36],"relaxing":[37],"assumption":[39],"architectural":[41],"symmetry,":[42],"it":[43],"is":[44],"possible":[46],"for":[47],"smaller":[48],"actors":[49,105,127],"to":[50,55,63,115],"achieve":[51],"comparable":[52],"policy":[53],"their":[56],"symmetric":[57],"counterparts.":[58],"Our":[59],"experiments":[60],"show":[61],"up":[62],"99%":[64],"reduction":[65,75,96],"number":[68],"weights":[71],"with":[72],"an":[73],"average":[74],"77":[77],"%":[78],"over":[79],"multiple":[80,126],"on":[83],"9":[84],"independent":[85],"tasks.":[86],"Given":[87],"that":[88,113],"reducing":[89],"complexity":[91],"results":[92],"a":[94],"direct":[95],"run-time":[98],"inference":[99],"cost,":[100],"we":[101],"believe":[102],"configurations":[103],"aspects":[109],"design":[112],"deserve":[114],"be":[116],"considered":[117],"independently,":[118],"particularly":[119],"resource-constrained":[121],"applications":[122],"or":[123],"deploying":[125],"simultaneously.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2022-07-25T00:00:00"}