{"id":"https://openalex.org/W4405314593","doi":"https://doi.org/10.1007/978-981-96-0814-0_27","title":"Enhancing Embedding and\u00a0Hierarchical Reward Shaping for\u00a0Multi-Hop Reasoning with\u00a0Reinforcement Learning","display_name":"Enhancing Embedding and\u00a0Hierarchical Reward Shaping for\u00a0Multi-Hop Reasoning with\u00a0Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4405314593","doi":"https://doi.org/10.1007/978-981-96-0814-0_27"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-96-0814-0_27","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-0814-0_27","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":"book-chapter","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/A5070458251","display_name":"Heng Li","orcid":"https://orcid.org/0000-0003-4434-254X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heng Li","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, 510631, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, 510631, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004261126","display_name":"Jinhui Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Wei","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, 510631, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, 510631, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102086350","display_name":"Jicheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicheng Yu","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, 510631, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, 510631, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030884785","display_name":"Yuncheng Jiang","orcid":"https://orcid.org/0000-0002-0402-5382"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuncheng Jiang","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, 510631, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, 510631, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070458251"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.604,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86593293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"429"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9869999885559082,"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":0.9836000204086304,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8217171430587769},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7811404466629028},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6182178258895874},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.5354030132293701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4467865228652954},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10888791084289551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217171430587769},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7811404466629028},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6182178258895874},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.5354030132293701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467865228652954},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10888791084289551}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-96-0814-0_27","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-0814-0_27","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":[{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1512387364","https://openalex.org/W1533230146","https://openalex.org/W1756422141","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2119717200","https://openalex.org/W2127795553","https://openalex.org/W2250635077","https://openalex.org/W2725395424","https://openalex.org/W2728059831","https://openalex.org/W2769099080","https://openalex.org/W2889344053","https://openalex.org/W2910396842","https://openalex.org/W2914592219","https://openalex.org/W2950393809","https://openalex.org/W2962886429","https://openalex.org/W2963157366","https://openalex.org/W2966298461","https://openalex.org/W3098682001","https://openalex.org/W3100187427","https://openalex.org/W3103296573","https://openalex.org/W3132016049","https://openalex.org/W3198686057","https://openalex.org/W3209619108","https://openalex.org/W4224324695","https://openalex.org/W4292635665","https://openalex.org/W4385863765","https://openalex.org/W6718112784"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2117210722","https://openalex.org/W2589759689","https://openalex.org/W4405141166","https://openalex.org/W2081900870","https://openalex.org/W1978191894","https://openalex.org/W2390279801","https://openalex.org/W4306904969"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
