{"id":"https://openalex.org/W3014728935","doi":"https://doi.org/10.1109/cog47356.2020.9231687","title":"Action Space Shaping in Deep Reinforcement Learning","display_name":"Action Space Shaping in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3014728935","doi":"https://doi.org/10.1109/cog47356.2020.9231687","mag":"3014728935"},"language":"en","primary_location":{"id":"doi:10.1109/cog47356.2020.9231687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231687","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 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":"2020 IEEE Conference on Games (CoG)","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/2004.00980","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574"},"institutions":[{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"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":true,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009506955","display_name":"Christian Scheller","orcid":"https://orcid.org/0000-0002-9624-1487"},"institutions":[{"id":"https://openalex.org/I2972652528","display_name":"FHNW University of Applied Sciences and Arts","ror":"https://ror.org/04mq2g308","country_code":"CH","type":"education","lineage":["https://openalex.org/I2972652528"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Scheller","raw_affiliation_strings":["Institute for Data Science, University of Applied Sciences Northwestern Switzerland, Windisch, Swizerland","University of Applied Sciences Northwestern Switzerland,Institute for Data Science,Windisch,Swizerland"],"affiliations":[{"raw_affiliation_string":"Institute for Data Science, University of Applied Sciences Northwestern Switzerland, Windisch, Swizerland","institution_ids":["https://openalex.org/I2972652528"]},{"raw_affiliation_string":"University of Applied Sciences Northwestern Switzerland,Institute for Data Science,Windisch,Swizerland","institution_ids":["https://openalex.org/I2972652528"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"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":"Ville Hautamaki","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","University of Eastern Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048689678"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"],"apc_list":null,"apc_paid":null,"fwci":1.3411,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83773976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8092358112335205},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.7059125304222107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5960490703582764},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5505448579788208},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.5305156111717224},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5047701597213745},{"id":"https://openalex.org/keywords/action-learning","display_name":"Action learning","score":0.47057148814201355},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43159496784210205},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42897239327430725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711391091346741},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3112673759460449},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14792516827583313},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.13697278499603271},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12573575973510742},{"id":"https://openalex.org/keywords/teaching-method","display_name":"Teaching method","score":0.10769903659820557},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.08520177006721497},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07948550581932068}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8092358112335205},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.7059125304222107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5960490703582764},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5505448579788208},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.5305156111717224},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5047701597213745},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.47057148814201355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43159496784210205},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42897239327430725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711391091346741},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3112673759460449},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14792516827583313},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.13697278499603271},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12573575973510742},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.10769903659820557},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.08520177006721497},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07948550581932068},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cog47356.2020.9231687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog47356.2020.9231687","pdf_url":null,"source":{"id":"https://openalex.org/S4306498668","display_name":"2020 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":"2020 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.00980","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00980","pdf_url":"https://arxiv.org/pdf/2004.00980","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":"","raw_type":"text"},{"id":"mag:3014728935","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2004.00980","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.2004.00980","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.00980","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.00980","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00980","pdf_url":"https://arxiv.org/pdf/2004.00980","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014728935.pdf","grobid_xml":"https://content.openalex.org/works/W3014728935.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W1522301498","https://openalex.org/W1777239053","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2215378786","https://openalex.org/W2480004914","https://openalex.org/W2553701371","https://openalex.org/W2592076308","https://openalex.org/W2736601468","https://openalex.org/W2740828027","https://openalex.org/W2749807327","https://openalex.org/W2751516180","https://openalex.org/W2769883686","https://openalex.org/W2785379783","https://openalex.org/W2810602713","https://openalex.org/W2907502844","https://openalex.org/W2941355526","https://openalex.org/W2962693466","https://openalex.org/W2962832483","https://openalex.org/W2963094322","https://openalex.org/W2963641140","https://openalex.org/W2963771109","https://openalex.org/W2963871073","https://openalex.org/W2963948533","https://openalex.org/W2963985863","https://openalex.org/W2964043796","https://openalex.org/W2964182681","https://openalex.org/W2966556569","https://openalex.org/W2975746467","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W2997756832","https://openalex.org/W3005014633","https://openalex.org/W3012086196","https://openalex.org/W3013028018","https://openalex.org/W3037207827","https://openalex.org/W4394672593","https://openalex.org/W6602057636","https://openalex.org/W6631190155","https://openalex.org/W6638088447","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6704571135","https://openalex.org/W6721634521","https://openalex.org/W6729788943","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6743660412","https://openalex.org/W6743756900","https://openalex.org/W6747473740","https://openalex.org/W6748314335","https://openalex.org/W6748638692","https://openalex.org/W6752963931","https://openalex.org/W6755612348","https://openalex.org/W6757797181","https://openalex.org/W6761839350","https://openalex.org/W6769022465","https://openalex.org/W6772421901","https://openalex.org/W6773682172","https://openalex.org/W6774923775","https://openalex.org/W6775250179","https://openalex.org/W6780225908","https://openalex.org/W6780559895","https://openalex.org/W6947956204"],"related_works":["https://openalex.org/W3094236223","https://openalex.org/W3189943185","https://openalex.org/W113028485","https://openalex.org/W3094113003","https://openalex.org/W1543837481","https://openalex.org/W3107227009","https://openalex.org/W2946669606","https://openalex.org/W3212146301","https://openalex.org/W2575120333","https://openalex.org/W1584210162","https://openalex.org/W3009803017","https://openalex.org/W3015592223","https://openalex.org/W3012544020","https://openalex.org/W2753986748","https://openalex.org/W1564312725","https://openalex.org/W3041878969","https://openalex.org/W3200372272","https://openalex.org/W2808007596","https://openalex.org/W1520863891","https://openalex.org/W1977655452"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,11],"(RL)":[2],"has":[3],"been":[4],"successful":[5,95],"in":[6,9,74,108],"training":[7],"agents":[8],"various":[10],"environments,":[12,110],"including":[13],"video":[14,75],"games.":[15],"However,":[16],"such":[17],"work":[18],"modifies":[19],"and":[20,36,86],"shrinks":[21],"the":[22,26,39,54,104],"action":[23,67],"space":[24,68],"from":[25],"game's":[27],"original.":[28],"This":[29],"is":[30,43],"to":[31,37,62,102,117],"avoid":[32],"trying":[33],"\"pointless\"":[34],"actions":[35,85,90],"ease":[38,103],"implementation.":[40],"Currently,":[41],"this":[42,58],"mostly":[44],"done":[45],"based":[46],"on":[47,65],"intuition,":[48],"with":[49],"little":[50],"systematic":[51],"research":[52],"supporting":[53],"design":[55],"decisions.":[56],"In":[57],"work,":[59],"we":[60,100],"aim":[61],"gain":[63],"insight":[64],"these":[66,98],"modifications":[69],"by":[70,111],"conducting":[71],"extensive":[72],"experiments":[73],"game":[76],"environments.":[77],"Our":[78],"results":[79],"show":[80],"how":[81],"domain-specific":[82],"removal":[83],"of":[84,88,106],"discretization":[87],"continuous":[89],"can":[91],"be":[92],"crucial":[93],"for":[94],"learning.":[96],"With":[97],"insights,":[99],"hope":[101],"use":[105],"RL":[107],"new":[109],"clarifying":[112],"what":[113],"action-spaces":[114],"are":[115],"easy":[116],"learn.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
