{"id":"https://openalex.org/W4385489433","doi":"https://doi.org/10.1145/3594315.3594399","title":"Stable Control Policy and Transferable Reward Function via Inverse Reinforcement Learning","display_name":"Stable Control Policy and Transferable Reward Function via Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-03-17","ids":{"openalex":"https://openalex.org/W4385489433","doi":"https://doi.org/10.1145/3594315.3594399"},"language":"en","primary_location":{"id":"doi:10.1145/3594315.3594399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594315.3594399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594315.3594399","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3594315.3594399","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111010097","display_name":"Keyu Wu","orcid":"https://orcid.org/0000-0002-8572-6016"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Wu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-8572-6016","affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030271803","display_name":"Fengge Wu","orcid":"https://orcid.org/0000-0002-1958-8321"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengge Wu","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-1958-8321","affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504810","display_name":"Yijun Lin","orcid":"https://orcid.org/0000-0001-8173-7116"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Lin","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-8173-7116","affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069584904","display_name":"Junsuo Zhao","orcid":"https://orcid.org/0000-0001-8950-4157"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsuo Zhao","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-8950-4157","affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2057,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4090239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"742"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9710000157356262,"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/computer-science","display_name":"Computer science","score":0.7122122049331665},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6523646712303162},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5663776397705078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5647134780883789},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5312582850456238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5151144862174988},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5142495036125183},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.495190292596817},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49487441778182983},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4886358380317688},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46124595403671265},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.433206707239151},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13672226667404175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12100985646247864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122122049331665},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6523646712303162},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5663776397705078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5647134780883789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5312582850456238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5151144862174988},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5142495036125183},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.495190292596817},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49487441778182983},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4886358380317688},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46124595403671265},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.433206707239151},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13672226667404175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12100985646247864},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3594315.3594399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594315.3594399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594315.3594399","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3594315.3594399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3594315.3594399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3594315.3594399","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385489433.pdf","grobid_xml":"https://content.openalex.org/works/W4385489433.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W152055444","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2145680191","https://openalex.org/W2153177812","https://openalex.org/W2982316857","https://openalex.org/W2990747716","https://openalex.org/W3016705845","https://openalex.org/W3103078873","https://openalex.org/W3208979922","https://openalex.org/W4213377513"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4281847915","https://openalex.org/W2075445622"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2,14],"(IRL)":[3],"can":[4,44],"solve":[5,100],"the":[6,25,38,62,93,101,131,138,156,162],"problem":[7,102],"of":[8,41],"complex":[9],"reward":[10,39,87,163],"function":[11,40,88,164],"shaping":[12],"by":[13,91,142,166],"from":[15],"expert":[16,26,115],"data.":[17,116],"However,":[18],"it":[19],"is":[20,28,33,105],"challenging":[21,106],"to":[22,35,47,56,67,79,107,129],"train":[23,108],"when":[24],"data":[27],"insufficient,":[29],"and":[30,85,96,126,159],"its":[31],"stability":[32],"difficult":[34],"guarantee.":[36],"Moreover,":[37],"mainstream":[42],"IRL":[43,77,104],"only":[45],"adapt":[46],"subtle":[48],"environmental":[49],"changes.":[50],"It":[51],"cannot":[52],"be":[53,68],"directly":[54],"transferred":[55],"a":[57,81,110,136],"similar":[58],"task":[59],"scenario,":[60],"so":[61],"generalization":[63],"ability":[64],"still":[65],"needs":[66],"improved.":[69],"To":[70],"address":[71,130],"these":[72],"issues,":[73],"we":[74,99,118],"propose":[75],"an":[76],"algorithm":[78,168],"obtain":[80],"stable":[82],"control":[83,139,146],"policy":[84,140],"transferable":[86],"(ST-IRL).":[89],"Firstly,":[90],"introducing":[92],"Wasserstein":[94],"metric":[95],"adversarial":[97],"training,":[98],"that":[103],"in":[109,148,154],"new":[111],"environment":[112],"with":[113],"little":[114],"Secondly,":[117],"add":[119],"state":[120],"marginal":[121],"matching":[122],"(SMM),":[123],"hyperparameter":[124],"comparison":[125],"optimizer":[127],"evaluation":[128],"model's":[132],"generalisability":[133],"problem.":[134],"As":[135],"result,":[137],"obtained":[141,165],"ST-IRL":[143],"achieves":[144],"outstanding":[145],"results":[147],"all":[149],"four":[150],"Mujoco":[151],"benchmarks.":[152],"Furthermore,":[153],"both":[155],"custom":[157],"Ant":[158],"PointMaze":[160],"environments,":[161],"our":[167],"exhibits":[169],"promising":[170],"transferability.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}