{"id":"https://openalex.org/W7128501865","doi":"https://doi.org/10.1007/978-3-032-15638-9_30","title":"Towards Generalizing Deep Reinforcement Learning Algorithms for Real World Applications","display_name":"Towards Generalizing Deep Reinforcement Learning Algorithms for Real World Applications","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128501865","doi":"https://doi.org/10.1007/978-3-032-15638-9_30"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-15638-9_30","doi":"https://doi.org/10.1007/978-3-032-15638-9_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-15638-9_30","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7128536314","display_name":"Computational Intelligence"},"type":"conference-paper","is_traditional":true,"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/A5073584081","display_name":"Daniel K. Ruiru","orcid":"https://orcid.org/0000-0003-3197-8821","observed_orcids":["https://orcid.org/0000-0003-3197-8821"]},"institutions":[{"id":"https://openalex.org/I161372803","display_name":"Strathmore University","ror":"https://ror.org/047dnqw48","country_code":"KE","type":"education","lineage":["https://openalex.org/I161372803"]},{"id":"https://openalex.org/I48825208","display_name":"Universit\u00e9 Paris 8","ror":"https://ror.org/04wez5e68","country_code":"FR","type":"education","lineage":["https://openalex.org/I48825208"]}],"countries":["FR","KE"],"is_corresponding":true,"raw_author_name":"Daniel Ruiru","raw_affiliation_strings":["Strathmore University, Nairobi, Kenya","Universit\u00e9 Paris 8, Saint-Denis, France"],"raw_orcid":"https://orcid.org/0000-0003-3197-8821","affiliations":[{"raw_affiliation_string":"Strathmore University, Nairobi, Kenya","institution_ids":["https://openalex.org/I161372803"]},{"raw_affiliation_string":"Universit\u00e9 Paris 8, Saint-Denis, France","institution_ids":["https://openalex.org/I48825208"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107874379","display_name":"Nicolas Jouandeau","orcid":"https://orcid.org/0000-0001-6902-4324","observed_orcids":["https://orcid.org/0000-0001-6902-4324"]},"institutions":[{"id":"https://openalex.org/I48825208","display_name":"Universit\u00e9 Paris 8","ror":"https://ror.org/04wez5e68","country_code":"FR","type":"education","lineage":["https://openalex.org/I48825208"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Jouandeau","raw_affiliation_strings":["Universit\u00e9 Paris 8, Saint-Denis, France"],"raw_orcid":"https://orcid.org/0000-0001-6902-4324","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris 8, Saint-Denis, France","institution_ids":["https://openalex.org/I48825208"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034369274","display_name":"Dickson Odhiambo Owuor","orcid":"https://orcid.org/0000-0002-0968-5742","observed_orcids":["https://orcid.org/0000-0002-0968-5742","https://orcid.org/0009-0009-0553-7302"]},"institutions":[{"id":"https://openalex.org/I161372803","display_name":"Strathmore University","ror":"https://ror.org/047dnqw48","country_code":"KE","type":"education","lineage":["https://openalex.org/I161372803"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Dickson Owuor","raw_affiliation_strings":["Strathmore University, Nairobi, Kenya"],"raw_orcid":"https://orcid.org/0000-0002-0968-5742","affiliations":[{"raw_affiliation_string":"Strathmore University, Nairobi, Kenya","institution_ids":["https://openalex.org/I161372803"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073584081"],"corresponding_institution_ids":["https://openalex.org/I161372803","https://openalex.org/I48825208"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04727316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.0,"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.7870000004768372},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.9419999718666077},{"id":"https://openalex.org/keywords/domain-randomization","display_name":"domain randomization","score":0.9819999933242798},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.9779999852180481},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.7870000004768372},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8899999856948853},{"id":"https://openalex.org/keywords/crop-production","display_name":"crop production","score":0.9169999957084656},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8827999830245972},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8810999989509583},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7627999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6710000038146973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5738000273704529},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C204243189","wikidata":"https://www.wikidata.org/wiki/Q1363085","display_name":"Randomization","level":3,"score":0.47600001096725464},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-15638-9_30","doi":"https://doi.org/10.1007/978-3-032-15638-9_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-15638-9_30","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W1999085008","https://openalex.org/W2074403262","https://openalex.org/W2145339207","https://openalex.org/W2586751528","https://openalex.org/W2616841723","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2794657759","https://openalex.org/W2797527950","https://openalex.org/W2898436992","https://openalex.org/W2904815624","https://openalex.org/W2963426313","https://openalex.org/W2996355317","https://openalex.org/W3031673669","https://openalex.org/W3121342653","https://openalex.org/W3155958512","https://openalex.org/W4224220194","https://openalex.org/W4292395995","https://openalex.org/W4295185389","https://openalex.org/W4311556094","https://openalex.org/W4320561332","https://openalex.org/W4322743829","https://openalex.org/W4386514919","https://openalex.org/W4387459443","https://openalex.org/W4403733806","https://openalex.org/W4404314527","https://openalex.org/W4404351709","https://openalex.org/W4405767717","https://openalex.org/W4407903031"],"related_works":["https://openalex.org/W2979395451","https://openalex.org/W2999617596","https://openalex.org/W4388946990","https://openalex.org/W4412844226","https://openalex.org/W4408358475","https://openalex.org/W2916826721","https://openalex.org/W4400860528","https://openalex.org/W2898436992","https://openalex.org/W3009492911","https://openalex.org/W2903181768"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-02-11T00:00:00"}
