{"id":"https://openalex.org/W4415427799","doi":"https://doi.org/10.3233/faia251396","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","display_name":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427799","doi":"https://doi.org/10.3233/faia251396"},"language":null,"primary_location":{"id":"doi:10.3233/faia251396","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251396","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251396","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091606728","display_name":"Giuseppe Canonaco","orcid":"https://orcid.org/0000-0001-8647-6269"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giuseppe Canonaco","raw_affiliation_strings":["AI Research Dept. JPMorganChase Madrid, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Dept. JPMorganChase Madrid, ES","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047729153","display_name":"Leo Ardon","orcid":"https://orcid.org/0000-0003-4400-7127"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leo Ardon","raw_affiliation_strings":["AI Research Dept. JPMorganChase London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Dept. JPMorganChase London, UK","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036948935","display_name":"Alberto Pozanco","orcid":"https://orcid.org/0000-0002-3851-1311"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alberto Pozanco","raw_affiliation_strings":["AI Research Dept. JPMorganChase Madrid, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Dept. JPMorganChase Madrid, ES","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050512952","display_name":"Daniel Borrajo","orcid":"https://orcid.org/0000-0001-5282-0463"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Borrajo","raw_affiliation_strings":["AI Research Dept. JPMorganChase Madrid, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Dept. JPMorganChase Madrid, ES","institution_ids":["https://openalex.org/I1305429384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1305429384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6537642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.6100999712944031,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.6100999712944031,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8597999811172485},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.664900004863739},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.46700000762939453},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4652000069618225},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4544999897480011}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8597999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251396","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251396","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251396","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251396","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"use":[1,41],"of":[2,75,95,112,124,152],"Potential-Based":[3],"Reward":[4],"Shaping":[5],"(PBRS)":[6],"has":[7],"shown":[8],"great":[9],"promise":[10],"in":[11,20,92],"the":[12,26,67,71,76,86,93,108,113,118,149],"ongoing":[13],"research":[14],"effort":[15],"to":[16,40,106],"tackle":[17],"sample":[18,119],"inefficiency":[19],"Reinforcement":[21],"Learning":[22,137],"(RL).":[23],"However,":[24],"choosing":[25],"right":[27],"potential":[28,68],"function":[29,69,74,111],"remains":[30],"an":[31],"open":[32],"challenge.":[33],"Additionally,":[34],"RL":[35],"techniques":[36],"are":[37],"usually":[38],"constrained":[39],"a":[42,50,104,130,158],"finite":[43,90],"horizon":[44],"for":[45],"computational":[46],"limitations,":[47],"which":[48],"introduces":[49],"bias":[51,87],"when":[52],"using":[53],"PBRS.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,116,146],"first":[59],"build":[60],"some":[61],"theoretically-grounded":[62],"intuition":[63],"on":[64,126],"why":[65],"selecting":[66],"as":[70,103,154],"optimal":[72,109],"value":[73,110],"task":[77,133],"at":[78],"hand":[79],"produces":[80],"performance":[81,122,153],"advantages.":[82],"We":[83],"then":[84],"analyse":[85],"induced":[88],"by":[89],"horizons":[91],"context":[94],"PBRS":[96,125],"producing":[97],"novel":[98],"insights.":[99],"Finally,":[100],"leveraging":[101],"abstractions":[102],"way":[105],"approximate":[107],"given":[114],"task,":[115],"assess":[117],"efficiency":[120],"and":[121,134],"impact":[123],"four":[127],"environments":[128],"including":[129],"goal-oriented":[131],"navigation":[132],"three":[135],"Arcade":[136],"Environments":[138],"(ALE)":[139],"games.":[140],"Remarkably,":[141],"experimental":[142],"results":[143],"show":[144],"that":[145],"can":[147],"reach":[148],"same":[150],"level":[151],"CNN-based":[155],"solutions":[156],"with":[157],"simple":[159],"fully-connected":[160],"network.":[161]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}