{"id":"https://openalex.org/W4281250801","doi":"https://doi.org/10.48550/arxiv.2205.09123","title":"A2C is a special case of PPO","display_name":"A2C is a special case of PPO","publication_year":2022,"publication_date":"2022-05-18","ids":{"openalex":"https://openalex.org/W4281250801","doi":"https://doi.org/10.48550/arxiv.2205.09123"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.09123","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09123","pdf_url":"https://arxiv.org/pdf/2205.09123","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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.09123","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huang, Shengyi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Shengyi","raw_affiliation_strings":["Drexel University USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574","observed_orcids":["https://orcid.org/0000-0002-7479-4574"]},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kanervisto, Anssi","raw_affiliation_strings":["University of Eastern Finland Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013236820","display_name":"Antonin Raffin","orcid":"https://orcid.org/0000-0001-6036-6950","observed_orcids":["https://orcid.org/0000-0001-6036-6950"]},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raffin, Antonin","raw_affiliation_strings":["German Aerospace Center Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Aerospace Center Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082417441","display_name":"Weixun Wang","orcid":"https://orcid.org/0000-0002-2727-8948","observed_orcids":["https://orcid.org/0000-0002-2727-8948"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Weixun","raw_affiliation_strings":["Tianjin University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038686010","display_name":"Santiago Onta\u00f1\u00f3n","orcid":"https://orcid.org/0000-0002-9616-2981","observed_orcids":["https://orcid.org/0000-0002-9616-2981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Onta\u00f1\u00f3n, Santiago","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081912903","display_name":"Rousslan Fernand Julien Dossa","orcid":"https://orcid.org/0000-0003-0572-692X","observed_orcids":["https://orcid.org/0000-0003-0572-692X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dossa, Rousslan Fernand Julien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":34,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/a2c","display_name":"Advantage Actor-Critic","score":0.9330000281333923},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9959999918937683},{"id":"https://openalex.org/keywords/algorithm-equivalence","display_name":"algorithm equivalence","score":0.6669999957084656},{"id":"https://openalex.org/keywords/policy-gradient-optimization","display_name":"policy gradient optimization","score":0.5040000081062317},{"id":"https://openalex.org/keywords/game-ai","display_name":"game AI","score":0.7020000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5980756282806396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39901667833328247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3292451500892639}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.09123","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09123","pdf_url":"https://arxiv.org/pdf/2205.09123","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.09123","doi":"https://doi.org/10.48550/arxiv.2205.09123","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.09123","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.09123","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.09123","pdf_url":"https://arxiv.org/pdf/2205.09123","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281250801.pdf","grobid_xml":"https://content.openalex.org/works/W4281250801.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2736601468"],"related_works":["https://openalex.org/W4390938908","https://openalex.org/W4221160322","https://openalex.org/W4297900582","https://openalex.org/W2987102938","https://openalex.org/W7167912155","https://openalex.org/W2953691792","https://openalex.org/W3188220908","https://openalex.org/W7095008446","https://openalex.org/W2904284497","https://openalex.org/W3094535073"],"abstract_inverted_index":{"Advantage":[0],"Actor-critic":[1],"(A2C)":[2],"and":[3,27,59,78],"Proximal":[4],"Policy":[5],"Optimization":[6],"(PPO)":[7],"are":[8,29,88],"popular":[9],"deep":[10],"reinforcement":[11],"learning":[12],"algorithms":[13,31],"used":[14],"for":[15],"game":[16],"AI":[17],"in":[18],"recent":[19],"years.":[20],"A":[21],"common":[22],"understanding":[23],"is":[24,49],"that":[25],"A2C":[26,48,77],"PPO":[28,79],"separate":[30],"because":[32],"PPO's":[33],"clipped":[34],"objective":[35],"appears":[36],"significantly":[37],"different":[38],"than":[39],"A2C's":[40],"objective.":[41],"In":[42],"this":[43],"paper,":[44],"however,":[45],"we":[46,69],"show":[47],"a":[50],"special":[51],"case":[52],"of":[53],"PPO.":[54],"We":[55],"present":[56],"theoretical":[57],"justifications":[58],"pseudocode":[60],"analysis":[61],"to":[62],"demonstrate":[63],"why.":[64],"To":[65],"validate":[66],"our":[67],"claim,":[68],"conduct":[70],"an":[71],"empirical":[72],"experiment":[73],"using":[74],"\\texttt{Stable-baselines3},":[75],"showing":[76],"produce":[80],"the":[81],"\\textit{exact}":[82],"same":[83],"models":[84],"when":[85],"other":[86],"settings":[87],"controlled.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2022-05-23T00:00:00"}