{"id":"https://openalex.org/W4283265447","doi":"https://doi.org/10.1145/3529836.3529918","title":"Pseudo Reward and Action Importance Classification for Sparse Reward Problem","display_name":"Pseudo Reward and Action Importance Classification for Sparse Reward Problem","publication_year":2022,"publication_date":"2022-02-18","ids":{"openalex":"https://openalex.org/W4283265447","doi":"https://doi.org/10.1145/3529836.3529918"},"language":"en","primary_location":{"id":"doi:10.1145/3529836.3529918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529836.3529918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","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/A5075381733","display_name":"Qingtong Wu","orcid":"https://orcid.org/0000-0001-9081-0143"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingtong Wu","raw_affiliation_strings":["School of Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["School of Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073132517","display_name":"Yuanzhao Zhai","orcid":"https://orcid.org/0000-0003-1385-0074"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Zhai","raw_affiliation_strings":["School of Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["School of Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100779417","display_name":"Jie Luo","orcid":"https://orcid.org/0000-0002-0786-400X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Luo","raw_affiliation_strings":["School of Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075381733"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0546365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9617000222206116,"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"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7139240503311157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973680257797241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6463446617126465},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5852108597755432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5535816550254822},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4713772237300873},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.43018171191215515},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4242463707923889},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41686898469924927},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09253054857254028},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07557058334350586}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7139240503311157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973680257797241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463446617126465},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5852108597755432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5535816550254822},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4713772237300873},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.43018171191215515},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4242463707923889},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41686898469924927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09253054857254028},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07557058334350586},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3529836.3529918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529836.3529918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W142858861","https://openalex.org/W2296073425","https://openalex.org/W2581240229","https://openalex.org/W2583993537","https://openalex.org/W2626429629","https://openalex.org/W2762242067","https://openalex.org/W2786036274","https://openalex.org/W2909711564","https://openalex.org/W2963523627","https://openalex.org/W2963900541","https://openalex.org/W3100944043","https://openalex.org/W3142849873","https://openalex.org/W3174204459","https://openalex.org/W4287902759"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning(DRL)":[2],"has":[3],"witnessed":[4],"great":[5],"success":[6],"in":[7,15,29,44,78,123],"many":[8,45,79],"fields":[9],"like":[10],"robotics,":[11],"games,":[12],"self-driving":[13],"cars":[14],"recent":[16],"years.":[17],"However,":[18],"the":[19,30,39,99,128,138,144],"sparse":[20],"reward":[21,105],"problem":[22],"where":[23],"a":[24,35,87,103],"meager":[25],"amount":[26],"of":[27,42,102,143],"states":[28],"state":[31],"space":[32],"that":[33],"return":[34],"feedback":[36],"signal":[37],"hinders":[38],"widespread":[40],"application":[41],"DRL":[43],"real-world":[46],"tasks.":[47],"Reward":[48],"shaping":[49],"with":[50],"carefully":[51],"designed":[52],"intrinsic":[53,64,96],"rewards":[54,65],"provides":[55],"an":[56,112],"effective":[57],"way":[58],"to":[59,107,116,120],"relieve":[60],"it.":[61],"Nevertheless,":[62],"useful":[63],"need":[66],"rich":[67],"domain":[68],"knowledge":[69],"and":[70,111,132,140],"extensive":[71],"fine-tuning,":[72],"which":[73,91],"makes":[74],"this":[75,83],"approach":[76],"unavailable":[77],"cases.":[80],"To":[81],"solve":[82],"problem,":[84],"we":[85],"propose":[86],"framework":[88],"called":[89],"PRAIC":[90,100],"only":[92],"utilizes":[93],"roughly":[94],"defined":[95],"rewards.":[97],"Specifically,":[98],"consists":[101],"pseudo":[104],"network":[106,115],"extract":[108],"reward-related":[109],"features":[110],"action":[113],"importance":[114,122],"classify":[117],"actions":[118],"according":[119],"their":[121],"different":[124],"scenarios.":[125],"Experiments":[126],"on":[127],"multi-agent":[129],"particle":[130],"environment":[131],"Google":[133],"Research":[134],"Football":[135],"game":[136],"demonstrate":[137],"effectiveness":[139],"superior":[141],"performance":[142],"proposed":[145],"method.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}