{"id":"https://openalex.org/W4416750152","doi":"https://doi.org/10.1109/iros60139.2025.11245903","title":"Successor Features for Transfer in Alternating Markov Games","display_name":"Successor Features for Transfer in Alternating Markov Games","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750152","doi":"https://doi.org/10.1109/iros60139.2025.11245903"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083574844","display_name":"Sunny Amatya","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunny Amatya","raw_affiliation_strings":["Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812346","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-7423-6719"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013789785","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-0440-0912"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,School for Engineering of Matter, Transport, and Energy,Tempe,AZ,USA,85287","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453347","display_name":"Wenlong Zhang","orcid":"https://orcid.org/0000-0002-4046-2213"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlong Zhang","raw_affiliation_strings":["Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,School of Manufacturing Systems and Networks,Mesa,AZ,USA,85212","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17454","last_page":"17461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8511000275611877,"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":0.8511000275611877,"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":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12158","display_name":"Guidance and Control Systems","score":0.02630000002682209,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/successor-cardinal","display_name":"Successor cardinal","score":0.9336000084877014},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5587000250816345},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5404999852180481},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49070000648498535},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45669999718666077},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.42559999227523804},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.3903999924659729}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.9336000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5957000255584717},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5404999852180481},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5331000089645386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.29840001463890076},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2776731479","wikidata":"https://www.wikidata.org/wiki/Q15142682","display_name":"Policy transfer","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2551000118255615},{"id":"https://openalex.org/C207405024","wikidata":"https://www.wikidata.org/wiki/Q207348","display_name":"Semigroup","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1497337834","https://openalex.org/W1542941925","https://openalex.org/W2036103676","https://openalex.org/W2056584142","https://openalex.org/W2149347032","https://openalex.org/W2761465998","https://openalex.org/W2921955147","https://openalex.org/W2965163470","https://openalex.org/W3072315125","https://openalex.org/W3110979110","https://openalex.org/W3166816823","https://openalex.org/W3178729124","https://openalex.org/W3205025130","https://openalex.org/W4293183440","https://openalex.org/W4294690543","https://openalex.org/W4312354311","https://openalex.org/W4402194461"],"related_works":[],"abstract_inverted_index":{"This":[0,59],"paper":[1,75],"explores":[2],"successor":[3,22,80],"features":[4,23,81],"for":[5,29,123],"knowledge":[6,40],"transfer":[7,41,109,124],"in":[8,16,42,100,159],"zero-sum,":[9],"complete-information,":[10],"and":[11,48,84,113,152],"turn-based":[12,139],"games.":[13,116],"Prior":[14],"research":[15],"single-agent":[17],"systems":[18],"has":[19],"shown":[20],"that":[21,144],"can":[24,61,148],"provide":[25],"a":[26,86,128,138,160],"\"jump":[27],"start\"":[28],"agents":[30],"when":[31,65],"facing":[32],"new":[33],"tasks":[34,67],"with":[35,137,173],"varying":[36],"reward":[37],"structures.":[38],"However,":[39],"games":[43,83,99],"typically":[44],"relies":[45],"on":[46,54],"value":[47],"equilibrium":[49],"transfers,":[50],"which":[51],"heavily":[52],"depends":[53],"the":[55,66,108,121,130,133,145,166,181],"similarity":[56,131],"between":[57],"tasks.":[58],"reliance":[60],"lead":[62],"to":[63,82,96,178],"failures":[64],"differ":[68],"significantly.":[69],"To":[70],"address":[71,97],"this":[72,74],"issue,":[73],"presents":[76,85],"an":[77],"application":[78],"of":[79,110,120,132,163,180],"novel":[87],"algorithm":[88,106,147,168],"called":[89],"Game":[90],"Generalized":[91],"Policy":[92],"Improvement":[93],"(GGPI),":[94],"designed":[95],"Markov":[98],"multi-agent":[101],"reinforcement":[102],"learning.":[103],"The":[104],"proposed":[105],"enables":[107],"learning":[111],"values":[112],"policies":[114],"across":[115],"An":[117],"upper":[118],"bound":[119],"errors":[122],"is":[125],"derived":[126],"as":[127],"function":[129],"task.":[134],"Through":[135],"experiments":[136],"pursuer-evader":[140],"game,":[141],"we":[142],"demonstrate":[143],"GGPI":[146,167],"generate":[149],"high-reward":[150],"interactions":[151],"one-shot":[153],"policy":[154],"transfer.":[155],"When":[156],"further":[157],"tested":[158],"wider":[161],"set":[162],"initial":[164],"conditions,":[165],"achieves":[169],"higher":[170],"success":[171],"rates":[172],"improved":[174],"path":[175],"efficiency":[176],"compared":[177],"those":[179],"baseline":[182],"algorithms.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}