{"id":"https://openalex.org/W3199291429","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533509","title":"Planning-integrated Policy for Efficient Reinforcement Learning in Sparse-reward Environments","display_name":"Planning-integrated Policy for Efficient Reinforcement Learning in Sparse-reward Environments","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199291429","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533509","mag":"3199291429"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5039140844","display_name":"Christoper Wulur","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christoper Wulur","raw_affiliation_strings":["Universit\u00e4t Hamburg"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Universit\u00e4t Hamburg"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Universit\u00e4t Hamburg"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039140844"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55003837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9926000237464905,"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":0.9803000092506409,"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":0.8960806131362915},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.7952914237976074},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.724919319152832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082709074020386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5971754789352417},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.49187350273132324},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45867639780044556},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4500638544559479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44156646728515625},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43951216340065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11516767740249634}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8960806131362915},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7952914237976074},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.724919319152832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082709074020386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971754789352417},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.49187350273132324},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45867639780044556},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4500638544559479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44156646728515625},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43951216340065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11516767740249634},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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":53,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W90062671","https://openalex.org/W1491843047","https://openalex.org/W1777239053","https://openalex.org/W1999874108","https://openalex.org/W2047600880","https://openalex.org/W2061562262","https://openalex.org/W2101539915","https://openalex.org/W2157445228","https://openalex.org/W2171776966","https://openalex.org/W2396820603","https://openalex.org/W2436711315","https://openalex.org/W2580175322","https://openalex.org/W2741122588","https://openalex.org/W2787938642","https://openalex.org/W2788781499","https://openalex.org/W2789824229","https://openalex.org/W2889731659","https://openalex.org/W2900152462","https://openalex.org/W2962872206","https://openalex.org/W2963414638","https://openalex.org/W2964118020","https://openalex.org/W2964295739","https://openalex.org/W2969428710","https://openalex.org/W2984524734","https://openalex.org/W2995298643","https://openalex.org/W3034974382","https://openalex.org/W3103559770","https://openalex.org/W3118210634","https://openalex.org/W4214717370","https://openalex.org/W4287779179","https://openalex.org/W4288029271","https://openalex.org/W4289294484","https://openalex.org/W4293396018","https://openalex.org/W4302422232","https://openalex.org/W6603783860","https://openalex.org/W6650265722","https://openalex.org/W6677916085","https://openalex.org/W6683182819","https://openalex.org/W6718359804","https://openalex.org/W6732665253","https://openalex.org/W6741519989","https://openalex.org/W6742380005","https://openalex.org/W6742461812","https://openalex.org/W6748523217","https://openalex.org/W6748839928","https://openalex.org/W6754302822","https://openalex.org/W6756256016","https://openalex.org/W6767226293","https://openalex.org/W6771217966","https://openalex.org/W6778000925","https://openalex.org/W6779509257","https://openalex.org/W6788072495"],"related_works":["https://openalex.org/W1568779110","https://openalex.org/W804484174","https://openalex.org/W4244698559","https://openalex.org/W4246538999","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982"],"abstract_inverted_index":{"Model-free":[0],"reinforcement":[1],"learning":[2],"algorithms":[3],"can":[4],"learn":[5],"an":[6,81],"optimal":[7],"policy":[8,115],"from":[9],"experience":[10],"without":[11],"requiring":[12],"prior":[13],"knowledge.":[14],"However,":[15],"model-free":[16,125],"agents":[17],"require":[18],"vast":[19],"amounts":[20],"of":[21,77,85],"samples,":[22],"particularly":[23],"in":[24,46,80,105],"sparse":[25,47],"reward":[26,48],"environments":[27],"where":[28],"most":[29],"states":[30],"contain":[31],"zero":[32,108],"rewards.":[33],"We":[34,93],"developed":[35],"a":[36,60],"model-based":[37],"approach":[38],"to":[39,101],"tackle":[40],"the":[41,69,75,78,86,89,96,99],"high":[42],"sample":[43],"complexity":[44],"problem":[45],"settings":[49],"with":[50,107,120],"continuous":[51,124],"actions.":[52],"A":[53],"trained":[54],"world":[55],"model":[56],"is":[57],"queried":[58],"by":[59],"particle":[61],"swarm":[62],"optimization":[63],"(PSO)":[64],"planner":[65,97],"and":[66],"employed":[67],"as":[68],"action":[70],"selection":[71],"mechanism,":[72],"hence":[73],"taking":[74],"role":[76],"actor":[79],"actor-critic":[82],"architecture.":[83],"Parameters":[84],"PSO":[87],"regulate":[88],"agent's":[90],"exploration":[91],"rate.":[92],"show":[94],"that":[95],"aids":[98],"agent":[100],"discover":[102],"rewards":[103],"even":[104],"regions":[106],"value":[109],"gradient.":[110],"Our":[111],"simple":[112],"planning":[113],"integrated":[114],"architecture":[116],"learns":[117],"more":[118],"efficiently":[119],"fewer":[121],"samples":[122],"than":[123],"algorithms.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}