{"id":"https://openalex.org/W3206305573","doi":"https://doi.org/10.1109/iros51168.2021.9636234","title":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments","display_name":"PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3206305573","doi":"https://doi.org/10.1109/iros51168.2021.9636234","mag":"3206305573"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636234","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057825143","display_name":"Qihao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qihao Liu","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,MD,USA","Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Sensing and Robotics,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767801","display_name":"Yujia Wang","orcid":"https://orcid.org/0000-0002-6733-4967"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujia Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071006392","display_name":"Xiaofeng Liu","orcid":"https://orcid.org/0000-0001-5024-9187"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5627","last_page":"5634"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.9122440814971924},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8314905166625977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6837103366851807},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.6165350079536438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547095000743866},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.4272725582122803},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3643520772457123}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.9122440814971924},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8314905166625977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837103366851807},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6165350079536438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547095000743866},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.4272725582122803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3643520772457123},{"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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636234","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W1974150877","https://openalex.org/W1988030247","https://openalex.org/W1996818689","https://openalex.org/W2099746672","https://openalex.org/W2127941149","https://openalex.org/W2132737349","https://openalex.org/W2158782408","https://openalex.org/W2168231600","https://openalex.org/W2280163991","https://openalex.org/W2345072837","https://openalex.org/W2417786368","https://openalex.org/W2575705757","https://openalex.org/W2770298516","https://openalex.org/W2779977383","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2787938642","https://openalex.org/W2788781499","https://openalex.org/W2793035934","https://openalex.org/W2810602713","https://openalex.org/W2894662639","https://openalex.org/W2905606790","https://openalex.org/W2912222576","https://openalex.org/W2949161920","https://openalex.org/W2950395671","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963712109","https://openalex.org/W2963790038","https://openalex.org/W2963938771","https://openalex.org/W2963940579","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964096423","https://openalex.org/W2964118020","https://openalex.org/W2968340082","https://openalex.org/W2996031640","https://openalex.org/W3000146453","https://openalex.org/W3099518626","https://openalex.org/W3101552411","https://openalex.org/W4297797010","https://openalex.org/W4297804636","https://openalex.org/W4300799055","https://openalex.org/W4394662461","https://openalex.org/W6636881020","https://openalex.org/W6679154944","https://openalex.org/W6679393576","https://openalex.org/W6684859321","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6735579001","https://openalex.org/W6740801417","https://openalex.org/W6747092830","https://openalex.org/W6748271565","https://openalex.org/W6748523217","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6749032995","https://openalex.org/W6749859622","https://openalex.org/W6755459763","https://openalex.org/W6757438168","https://openalex.org/W6770580189","https://openalex.org/W6771739536","https://openalex.org/W6780559895","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W2751208925","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W2080951048","https://openalex.org/W3011883280","https://openalex.org/W2390346111","https://openalex.org/W2369082698"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3,51],"made":[4],"remarkable":[5],"achievements,":[6],"but":[7],"it":[8],"still":[9],"suffers":[10],"from":[11,190],"inadequate":[12],"exploration":[13,103,145],"strategies,":[14],"sparse":[15,172],"reward":[16,20,175],"signals,":[17],"and":[18,55,69,104,146,198],"deceptive":[19],"functions.":[21],"To":[22,101],"alleviate":[23],"these":[24],"problems,":[25],"a":[26],"Population-guided":[27],"Novelty":[28,107],"Search":[29,108],"(PNS)":[30],"parallel":[31],"learning":[32],"method":[33],"is":[34,43,110,153],"proposed":[35],"in":[36,83,112,149,155,169,195],"this":[37],"paper.":[38],"In":[39],"PNS,":[40],"the":[41,63,71,86,89,98,106,130,156,166],"population":[42],"divided":[44],"into":[45],"multiple":[46],"sub-populations,":[47],"each":[48],"of":[49,88,141],"which":[50],"one":[52],"chief":[53,60,99,114],"agent":[54,61,115],"several":[56],"exploring":[57,67,78],"agents.":[58],"The":[59,77,139],"evaluates":[62],"policies":[64,82,96,118,188],"learned":[65],"by":[66],"agents":[68,79,184],"shares":[70],"optimal":[72,90],"policy":[73,91,136],"with":[74,85,119,171],"all":[75],"sub-populations.":[76],"learn":[80,186],"their":[81,95],"collaboration":[84],"guidance":[87],"and,":[92],"simultaneously,":[93],"upload":[94],"to":[97,116,129,143,185],"agent.":[100],"balance":[102],"exploitation,":[105],"(NS)":[109],"employed":[111],"every":[113],"encourage":[117],"high":[120],"novelty":[121],"while":[122],"maximizing":[123],"per-episode":[124],"performance.":[125],"We":[126,177],"apply":[127],"PNS":[128,142,181],"twin":[131],"delayed":[132,174],"deep":[133],"deterministic":[134],"(TD3)":[135],"gradient":[137],"algorithm.":[138],"effectiveness":[140],"promote":[144],"improve":[147],"performance":[148],"continuous":[150],"control":[151,187],"domains":[152],"demonstrated":[154],"experimental":[157],"section.":[158],"Notably,":[159],"PNS-TD3":[160],"achieves":[161],"rewards":[162],"that":[163,180],"far":[164],"exceed":[165],"SOTA":[167],"methods":[168],"environments":[170],"or":[173],"signals.":[176],"also":[178],"demonstrate":[179],"enables":[182],"robotic":[183],"directly":[189],"pixels":[191],"for":[192],"sparse-reward":[193],"manipulation":[194],"both":[196],"simulated":[197],"real-world":[199],"settings.":[200]},"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":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}