{"id":"https://openalex.org/W2593464192","doi":"https://doi.org/10.1145/3029798.3038421","title":"Potential Based Reward Shaping Using Learning to Rank","display_name":"Potential Based Reward Shaping Using Learning to Rank","publication_year":2017,"publication_date":"2017-03-06","ids":{"openalex":"https://openalex.org/W2593464192","doi":"https://doi.org/10.1145/3029798.3038421","mag":"2593464192"},"language":"en","primary_location":{"id":"doi:10.1145/3029798.3038421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029798.3038421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction","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/A5059105394","display_name":"Syed Ali Raza","orcid":"https://orcid.org/0000-0001-6570-4808"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Syed Ali Raza","raw_affiliation_strings":["University of Technology, Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology, Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011812136","display_name":"Mary\u2010Anne Williams","orcid":"https://orcid.org/0000-0002-1047-0503"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mary-Anne Williams","raw_affiliation_strings":["University of Technology, Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology, Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059105394"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01841542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"94","issue":null,"first_page":"261","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.989799976348877,"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"}},{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9786999821662903,"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/ranking","display_name":"Ranking (information retrieval)","score":0.8477143049240112},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7945349216461182},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.7340893745422363},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6786895394325256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6708748936653137},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6458749771118164},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6138210892677307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5840033292770386},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5675109028816223},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5483475923538208},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4781844913959503},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46600279211997986},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44061264395713806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1966170370578766},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16438999772071838},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11084407567977905}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8477143049240112},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7945349216461182},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.7340893745422363},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6786895394325256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708748936653137},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6458749771118164},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6138210892677307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5840033292770386},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5675109028816223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5483475923538208},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4781844913959503},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46600279211997986},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44061264395713806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1966170370578766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16438999772071838},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11084407567977905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3029798.3038421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029798.3038421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction","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":5,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2035720976","https://openalex.org/W2101626488","https://openalex.org/W2156869222","https://openalex.org/W2491675558"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W3160516639","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W2971071571","https://openalex.org/W2798835721","https://openalex.org/W4225571923","https://openalex.org/W2387658907","https://openalex.org/W3212257828"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22,32,47,50,59,63,73,82,88,100,105],"novel":[4],"method":[5,115],"for":[6,15],"the":[7,79,92,113,118],"computation":[8],"of":[9,43,76,94],"potential":[10,16,33,83],"function":[11,84],"using":[12,62,87],"human":[13],"input":[14],"based":[17],"reward":[18],"shaping.":[19],"It":[20],"defines":[21],"ranking":[23,60,67,75],"over":[24],"state":[25],"space":[26],"which":[27],"is":[28,69,85],"used":[29,56,70],"to":[30,40,57,71],"define":[31,72],"function.":[34,90],"Specifically,":[35],"it":[36,98],"seeks":[37],"multiple,":[38],"partial":[39],"full,":[41],"rankings":[42,54],"robot's":[44],"states":[45],"from":[46],"user":[48],"in":[49,104],"HRI":[51],"scenario.":[52],"These":[53],"are":[55],"learn":[58],"model":[61,68],"learning-to-rank":[64],"algorithm.":[65],"The":[66,108],"complete":[74],"states.":[77],"From":[78],"ranked":[80],"states,":[81],"computed":[86],"mapping":[89],"For":[91],"proof":[93],"concept,":[95],"we":[96],"compared":[97],"with":[99],"base-line":[101],"reinforcement":[102],"learner":[103],"simulated":[106],"domain.":[107],"empirical":[109],"results":[110],"showed":[111],"that":[112],"proposed":[114],"clearly":[116],"outperformed":[117],"benchmark.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}