{"id":"https://openalex.org/W7034091645","doi":null,"title":"THEORY AND APPLICATION OF REWARD SHAPING IN REINFORCEMENT LEARNING","display_name":"THEORY AND APPLICATION OF REWARD SHAPING IN REINFORCEMENT LEARNING","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W7034091645"},"language":"en","primary_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/10797","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/10797","pdf_url":"http://hdl.handle.net/2142/10797","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2142/10797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059441221","display_name":"Adam Laud","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adam Daniel Laud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5059441221"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reward-shaping","display_name":"reward shaping","score":1.0},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9259999990463257},{"id":"https://openalex.org/keywords/prior-knowledge","display_name":"prior knowledge","score":0.7860000133514404},{"id":"https://openalex.org/keywords/learning-efficiency","display_name":"learning efficiency","score":0.7580000162124634},{"id":"https://openalex.org/keywords/grid-world","display_name":"grid world","score":0.699999988079071},{"id":"https://openalex.org/keywords/large-state-spaces","display_name":"large state spaces","score":0.628000020980835},{"id":"https://openalex.org/keywords/stochastic-actions","display_name":"stochastic actions","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7836999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6236000061035156},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:www.ideals.illinois.edu:2142/10797","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/10797","pdf_url":"http://hdl.handle.net/2142/10797","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.175.226","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.175.226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ideals.illinois.edu/bitstream/handle/2142/10797/Theory and Application of Reward Shaping in Reinforcement Learning.pdf?sequence=2","raw_type":"text"},{"id":"pmh:oai:www.ideals.illinois.edu:2142/81640","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/2142/81640","pdf_url":null,"source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/10797","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/10797","pdf_url":"http://hdl.handle.net/2142/10797","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7034091645.pdf","grobid_xml":"https://content.openalex.org/works/W7034091645.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1769460679","https://openalex.org/W7096434988","https://openalex.org/W3095669803","https://openalex.org/W1617610651","https://openalex.org/W2079247031","https://openalex.org/W2107297861","https://openalex.org/W2788455270","https://openalex.org/W7124284865","https://openalex.org/W3131041265","https://openalex.org/W1581412038"],"abstract_inverted_index":{"Applying":[0],"conventional":[1,292],"reinforcement":[2,293],"to":[3,28,53,75,127,133,139,164,174,217,238,296],"complex":[4,99],"domains":[5],"requires":[6],"the":[7,26,47,77,88,107,119,135,143,146,151,168,197,212,219,264,267,274],"use":[8],"of":[9,19,40,109,145,159,170,182],"an":[10,32,154],"overly":[11],"simplified":[12],"task":[13,283],"model,":[14,228],"or":[15],"a":[16,38,65,103,176,187,227,252,256,291,298,303],"large":[17,52,304],"amount":[18],"training":[20],"experience.":[21],"This":[22,207],"problem":[23],"results":[24],"from":[25],"need":[27],"experience":[29],"everything":[30],"about":[31],"environment":[33],"before":[34],"gaining":[35],"confidence":[36],"in":[37,98,131],"course":[39],"action.":[41],"But":[42],"for":[43,94,106,199],"most":[44,89,270],"interesting":[45],"problems,":[46],"domain":[48],"is":[49,85,142,173,191,196,215,243],"far":[50],"too":[51],"be":[54],"exhaustively":[55],"explored.":[56],"We":[57,101,245],"address":[58],"this":[59],"disparity":[60],"with":[61,211,249,307],"reward":[62,110,147,171,178,183,189,275,287],"shaping":[63,111,121,172,232,235,288],"-":[64],"technique":[66],"that":[67,112,184,272,285],"provides":[68],"localized":[69,82],"feedback":[70],"based":[71],"on":[72],"prior":[73,129,241],"knowledge":[74,130,242],"guide":[76],"learning":[78,84,136,294],"process.":[79,137],"By":[80],"using":[81],"advice,":[83],"focused":[86,166],"into":[87],"relevant":[90],"areas,":[91],"which":[92,149],"allows":[93],"efficient":[95],"optimization,":[96],"even":[97],"domains.":[100],"propose":[102],"complete":[104],"theory":[105,248],"process":[108],"demonstrates":[113,284],"how":[114,126],"it":[115],"accelerates":[116],"learning,":[117,167],"what":[118],"ideal":[120],"rewards":[122],"are":[123],"like,":[124],"and":[125,156,233,255],"express":[128],"order":[132,163],"enhance":[134],"Central":[138],"our":[140,247,286],"analysis":[141],"idea":[144],"horizon,":[148],"characterizes":[150],"delay":[152],"between":[153],"action":[155,202,221],"accurate":[157],"estimation":[158],"its":[160],"value.":[161,193],"In":[162,261],"maintain":[165],"goal":[169],"promote":[175],"low":[177,188],"horizon.":[179],"One":[180],"type":[181],"always":[185],"generates":[186],"horizon":[190,276],"opportunity":[192,224],"Opportunity":[194],"value":[195,198,225],"choosing":[200],"one":[201],"rather":[203],"than":[204],"doing":[205],"nothing.":[206],"information,":[208],"when":[209],"combined":[210],"native":[213],"rewards,":[214],"enough":[216],"decide":[218],"best":[220],"immediately.":[222],"Using":[223],"as":[226,236],"we":[229],"suggest":[230],"subgoal":[231],"dynamic":[234],"techniques":[237,289],"communicate":[239],"whatever":[240],"available.":[244],"demonstrate":[246],"two":[250],"applications:":[251],"stochastic":[253,308],"gridworld,":[254],"bipedal":[257,281],"walking":[258,282],"control":[259],"task.":[260],"all":[262],"cases,":[263],"experiments":[265],"uphold":[266],"analytical":[268],"predictions;":[269],"notably":[271],"reducing":[273],"implies":[277],"faster":[278],"learning.":[279],"The":[280],"allow":[290],"algorithm":[295],"find":[297],"good":[299],"behavior":[300],"efficiently":[301],"despite":[302],"state":[305],"space":[306],"actions.":[309]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}