{"id":"https://openalex.org/W3092213025","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892256","title":"Learning Intrinsic Symbolic Rewards in Reinforcement Learning","display_name":"Learning Intrinsic Symbolic Rewards in Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3092213025","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892256","mag":"3092213025"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892256","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 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/A5002510185","display_name":"Hassam Ullah Sheikh","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hassam Ullah Sheikh","raw_affiliation_strings":["Intel Labs,United States","Intel Labs, United States"],"affiliations":[{"raw_affiliation_string":"Intel Labs,United States","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008832526","display_name":"Shauharda Khadka","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shauharda Khadka","raw_affiliation_strings":["Microsoft,United States","Microsoft, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft,United States","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013678286","display_name":"Santiago Miret","orcid":"https://orcid.org/0000-0002-5121-3853"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Santiago Miret","raw_affiliation_strings":["Intel Labs,United States","Intel Labs, United States"],"affiliations":[{"raw_affiliation_string":"Intel Labs,United States","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070857594","display_name":"Somdeb Majumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somdeb Majumdar","raw_affiliation_strings":["Intel Labs,United States","Intel Labs, United States"],"affiliations":[{"raw_affiliation_string":"Intel Labs,United States","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008537744","display_name":"Mariano Phielipp","orcid":"https://orcid.org/0009-0001-2753-1747"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariano Phielipp","raw_affiliation_strings":["Intel Labs,United States","Intel Labs, United States"],"affiliations":[{"raw_affiliation_string":"Intel Labs,United States","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs, United States","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002510185"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65314587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","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":0.9994999766349792,"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":0.9994999766349792,"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":0.996399998664856,"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":0.9688000082969666,"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":0.8674909472465515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532064914703369},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6779124736785889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6638939380645752},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6579364538192749},{"id":"https://openalex.org/keywords/learnability","display_name":"Learnability","score":0.5990490913391113},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5582131743431091},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5438852310180664},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5303690433502197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4555458128452301},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4168550670146942}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8674909472465515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532064914703369},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6779124736785889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638939380645752},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6579364538192749},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.5990490913391113},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5582131743431091},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5438852310180664},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5303690433502197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4555458128452301},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4168550670146942},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892256","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 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":49,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W1608057971","https://openalex.org/W1777239053","https://openalex.org/W1978970913","https://openalex.org/W2014394432","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2284330674","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2787387965","https://openalex.org/W2923189133","https://openalex.org/W2923682622","https://openalex.org/W2943810245","https://openalex.org/W2962749646","https://openalex.org/W2962858226","https://openalex.org/W2963262099","https://openalex.org/W2963296584","https://openalex.org/W2963523627","https://openalex.org/W2963672746","https://openalex.org/W2963761387","https://openalex.org/W2963864421","https://openalex.org/W2963985863","https://openalex.org/W2964096423","https://openalex.org/W2970272688","https://openalex.org/W2995509794","https://openalex.org/W2997502221","https://openalex.org/W3006670279","https://openalex.org/W3037812429","https://openalex.org/W4288359891","https://openalex.org/W4293842096","https://openalex.org/W4295549420","https://openalex.org/W4297797010","https://openalex.org/W6638088447","https://openalex.org/W6684921986","https://openalex.org/W6703271639","https://openalex.org/W6734129231","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6749859622","https://openalex.org/W6752296227","https://openalex.org/W6761920647","https://openalex.org/W6767151588","https://openalex.org/W6771936881","https://openalex.org/W6780106213"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2041126907","https://openalex.org/W2130711276"],"abstract_inverted_index":{"Learning":[0,13],"effective":[1,143],"policies":[2],"for":[3,86,145],"sparse":[4],"objectives":[5],"is":[6,18],"a":[7,67,100,111,158],"key":[8],"challenge":[9],"in":[10,73,123,129,166],"Deep":[11],"Reinforcement":[12],"(RL).":[14],"A":[15],"common":[16],"approach":[17],"to":[19,24,47,94,99,149],"design":[20],"task-related":[21],"dense":[22,49,71,139],"rewards":[23,30,51,72,140],"improve":[25],"task":[26],"learnability.":[27],"While":[28],"such":[29],"are":[31,55,141],"easily":[32],"interpreted,":[33],"they":[34],"rely":[35],"on":[36,119],"heuristics":[37],"and":[38,125,131],"domain":[39],"expertise.":[40],"Alternate":[41],"approaches":[42],"that":[43,69,136],"train":[44],"neural":[45,112],"networks":[46],"discover":[48],"surrogate":[50],"avoid":[52],"heuristics,":[53],"but":[54],"high-dimensional,":[56],"black-box":[57],"solutions":[58],"offering":[59],"little":[60],"interpretability.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,155],"present":[66],"method":[68,118],"discovers":[70],"the":[74,106,137,151],"form":[75],"of":[76,110],"low-dimensional":[77],"symbolic":[78],"trees":[79,89],"-":[80],"thus":[81],"making":[82],"them":[83],"more":[84],"tractable":[85],"analysis.":[87],"The":[88],"use":[90],"simple":[91],"functional":[92],"operators":[93],"map":[95],"an":[96,142,146],"agent's":[97],"observations":[98],"scalar":[101],"reward,":[102],"which":[103],"then":[104],"supervises":[105],"policy":[107,148],"gradient":[108],"learning":[109],"network":[113],"policy.":[114],"We":[115,134],"test":[116],"our":[117],"continuous":[120],"action":[121,127],"spaces":[122,128],"Mujoco":[124],"discrete":[126],"Atari":[130],"Pygame":[132],"environments.":[133],"show":[135],"discovered":[138],"signal":[144],"RL":[147],"solve":[150],"benchmark":[152],"tasks.":[153],"Notably,":[154],"significantly":[156],"outperform":[157],"widely":[159],"used,":[160],"contemporary":[161],"neural-network":[162],"based":[163],"reward-discovery":[164],"algorithm":[165],"all":[167],"environments":[168],"considered.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}