{"id":"https://openalex.org/W3157979152","doi":"https://doi.org/10.1109/iscas51556.2021.9401286","title":"Combined Reinforcement Learning via Artificial Potential Field: A Case Study in Pommerman","display_name":"Combined Reinforcement Learning via Artificial Potential Field: A Case Study in Pommerman","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3157979152","doi":"https://doi.org/10.1109/iscas51556.2021.9401286","mag":"3157979152"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5027617553","display_name":"Yuqi Zhu","orcid":"https://orcid.org/0000-0003-1951-7053"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqi Zhu","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000067683","display_name":"Shengze Li","orcid":"https://orcid.org/0000-0003-2160-8675"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengze Li","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741623","display_name":"Jieyuan Zhang","orcid":"https://orcid.org/0000-0003-2100-1312"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieyuan Zhang","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101775095","display_name":"Xinhai Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhai Xu","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027617553"],"corresponding_institution_ids":["https://openalex.org/I4210158522"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51856357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"5"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9887999892234802,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9184712171554565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478843331336975},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.745506227016449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6282040476799011},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5893025398254395},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5808861255645752},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5597977042198181},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43859216570854187},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15082836151123047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09202936291694641}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9184712171554565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478843331336975},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.745506227016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6282040476799011},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5893025398254395},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5808861255645752},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5597977042198181},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43859216570854187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15082836151123047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09202936291694641},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas51556.2021.9401286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2103120971","https://openalex.org/W2155027007","https://openalex.org/W2177274602","https://openalex.org/W2257979135","https://openalex.org/W2749928749","https://openalex.org/W2903006607","https://openalex.org/W2919115771","https://openalex.org/W2943197047","https://openalex.org/W2964043796","https://openalex.org/W2982316857","https://openalex.org/W2982365794","https://openalex.org/W2982667879","https://openalex.org/W2986185262","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4320341798","https://openalex.org/W6637967152","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6743802245","https://openalex.org/W6755224613","https://openalex.org/W6756851941","https://openalex.org/W6762119003","https://openalex.org/W6770202002"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Pommerman":[0,21,48,108],"is":[1,7,75],"a":[2,52,68,103],"recently-proposed":[3],"multi-agent":[4],"benchmark,":[5],"which":[6],"very":[8],"challenging":[9],"for":[10],"Reinforcement":[11],"Learning":[12],"(RL).":[13],"The":[14,88],"main":[15],"obstacles":[16],"to":[17,35,55,77,111],"adopt":[18],"RL":[19],"in":[20,45],"are":[22,99],"the":[23,46,79,93,107,112],"delayed":[24],"action":[25],"effects":[26],"and":[27,63,83,96,117],"sparse":[28],"rewards.":[29],"This":[30],"paper":[31],"presents":[32],"novel":[33],"approaches":[34],"mitigate":[36],"these":[37],"problems":[38],"by":[39],"introducing":[40],"Artificial":[41],"Potential":[42],"Field":[43],"(APF)":[44],"two-dimensional":[47],"world.":[49],"We":[50],"propose":[51],"new":[53,69],"framework":[54],"generate":[56],"hybrid":[57],"features":[58],"from":[59],"both":[60,100],"APF":[61,74],"computation":[62],"raw":[64],"environment":[65],"data.":[66],"Meanwhile,":[67],"reward":[70,98],"shaping":[71],"method":[72],"through":[73],"developed":[76],"give":[78],"learning":[80,94,114],"agent":[81],"faster":[82],"more":[84],"efficient":[85],"policy":[86],"iteration.":[87],"training":[89],"results":[90],"show":[91],"that":[92],"speed":[95],"convergence":[97],"improved":[101],"on":[102],"1v1":[104],"mode":[105],"of":[106],"game,":[109],"compared":[110],"conventional":[113],"algorithms,":[115],"A2C":[116],"ACKTR.":[118]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}