{"id":"https://openalex.org/W3209643201","doi":"https://doi.org/10.1007/978-3-030-89370-5_4","title":"Off-Policy Training for Truncated TD($$\\lambda $$) Boosted Soft Actor-Critic","display_name":"Off-Policy Training for Truncated TD($$\\lambda $$) Boosted Soft Actor-Critic","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3209643201","doi":"https://doi.org/10.1007/978-3-030-89370-5_4","mag":"3209643201"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-89370-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-89370-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5101984824","display_name":"Shiyu Huang","orcid":"https://orcid.org/0000-0003-0500-0141"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0500-0141","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049751916","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-5084-8590"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Huawei Noah Ark\u2019s Lab, Beijing, China","Huawei Noah Ark's Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah Ark\u2019s Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah Ark's Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341885","display_name":"Hang Su","orcid":"https://orcid.org/0000-0001-8294-6315"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8294-6315","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407476","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-7104-1921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["Huawei Noah Ark\u2019s Lab, Beijing, China","Huawei Noah Ark's Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah Ark\u2019s Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah Ark's Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Huawei Noah Ark\u2019s Lab, Beijing, China","Huawei Noah Ark's Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah Ark\u2019s Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah Ark's Lab, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443189","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0002-3228-9166"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3228-9166","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15089402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.7292741537094116},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49912071228027344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3939440846443176},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.3272266387939453},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.26025670766830444},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.09282821416854858}],"concepts":[{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.7292741537094116},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49912071228027344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3939440846443176},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3272266387939453},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.26025670766830444},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.09282821416854858},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-89370-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-89370-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W55051199","https://openalex.org/W64088143","https://openalex.org/W1514587017","https://openalex.org/W1757796397","https://openalex.org/W2100677568","https://openalex.org/W2100752967","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2411690432","https://openalex.org/W2593237273","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2787938642","https://openalex.org/W2902098903","https://openalex.org/W2904246096","https://openalex.org/W2914933231","https://openalex.org/W2949980113","https://openalex.org/W2951799221","https://openalex.org/W2962766894","https://openalex.org/W2964016927","https://openalex.org/W3011120880","https://openalex.org/W3139377883","https://openalex.org/W4285719527","https://openalex.org/W6600075554","https://openalex.org/W6633262331"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2951695430","https://openalex.org/W230091440","https://openalex.org/W4300891849","https://openalex.org/W2318687609","https://openalex.org/W91590591","https://openalex.org/W2390279801","https://openalex.org/W159772521","https://openalex.org/W2950100995","https://openalex.org/W2233261550"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
