{"id":"https://openalex.org/W3121342653","doi":"https://doi.org/10.1007/s10994-021-05961-4","title":"Challenges of real-world reinforcement learning: definitions, benchmarks and analysis","display_name":"Challenges of real-world reinforcement learning: definitions, benchmarks and analysis","publication_year":2021,"publication_date":"2021-04-22","ids":{"openalex":"https://openalex.org/W3121342653","doi":"https://doi.org/10.1007/s10994-021-05961-4","mag":"3121342653"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-05961-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05961-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05961-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05961-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008880429","display_name":"Gabriel Dulac-Arnold","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gabriel Dulac-Arnold","raw_affiliation_strings":["Google Research, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086990247","display_name":"Nir Levine","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nir Levine","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071714901","display_name":"Daniel J. Mankowitz","orcid":"https://orcid.org/0000-0002-4911-8275"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel J. Mankowitz","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101439736","display_name":"Jerry Li","orcid":"https://orcid.org/0000-0002-8774-826X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jerry Li","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056097740","display_name":"Cosmin P\u0103duraru","orcid":"https://orcid.org/0000-0002-1746-5467"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cosmin Paduraru","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059632022","display_name":"Sven Gowal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sven Gowal","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048229171","display_name":"Todd Hester","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Todd Hester","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008880429"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":45.4678,"has_fulltext":true,"cited_by_count":570,"citation_normalized_percentile":{"value":0.99885477,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"110","issue":"9","first_page":"2419","last_page":"2468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10603","display_name":"Smart Grid Energy Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12761","display_name":"Data Stream Mining Techniques","score":0.9865999817848206,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.868736743927002},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.8512360453605652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419722676277161},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.736761212348938},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6175714135169983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540547788143158},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5331513285636902},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5280980467796326},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4987764358520508},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4125971794128418},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34127628803253174},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10276326537132263}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.868736743927002},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.8512360453605652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419722676277161},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.736761212348938},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6175714135169983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540547788143158},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5331513285636902},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5280980467796326},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4987764358520508},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4125971794128418},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34127628803253174},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10276326537132263},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-021-05961-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05961-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05961-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-021-05961-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05961-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05961-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3121342653.pdf","grobid_xml":"https://content.openalex.org/works/W3121342653.grobid-xml"},"referenced_works_count":196,"referenced_works":["https://openalex.org/W40338364","https://openalex.org/W41554520","https://openalex.org/W166862392","https://openalex.org/W567721252","https://openalex.org/W569478347","https://openalex.org/W1518931405","https://openalex.org/W1854944386","https://openalex.org/W1931877416","https://openalex.org/W1973976093","https://openalex.org/W1982262386","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2061562262","https://openalex.org/W2072931156","https://openalex.org/W2097797606","https://openalex.org/W2102660061","https://openalex.org/W2104733512","https://openalex.org/W2106378743","https://openalex.org/W2109910161","https://openalex.org/W2120346334","https://openalex.org/W2121092017","https://openalex.org/W2121506959","https://openalex.org/W2121863487","https://openalex.org/W2134491302","https://openalex.org/W2145339207","https://openalex.org/W2167224731","https://openalex.org/W2167696704","https://openalex.org/W2168342951","https://openalex.org/W2168565265","https://openalex.org/W2173248099","https://openalex.org/W2186820913","https://openalex.org/W2215378786","https://openalex.org/W2256970469","https://openalex.org/W2257979135","https://openalex.org/W2267881773","https://openalex.org/W2280163991","https://openalex.org/W2344023930","https://openalex.org/W2394978111","https://openalex.org/W2396906324","https://openalex.org/W2401992734","https://openalex.org/W2427917354","https://openalex.org/W2465254145","https://openalex.org/W2504641290","https://openalex.org/W2512971201","https://openalex.org/W2523728418","https://openalex.org/W2529658650","https://openalex.org/W2530221730","https://openalex.org/W2559655401","https://openalex.org/W2562337727","https://openalex.org/W2575705757","https://openalex.org/W2596883012","https://openalex.org/W2604763608","https://openalex.org/W2612690371","https://openalex.org/W2614208603","https://openalex.org/W2616964725","https://openalex.org/W2624731731","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2739473244","https://openalex.org/W2750115194","https://openalex.org/W2750866482","https://openalex.org/W2754517384","https://openalex.org/W2767050701","https://openalex.org/W2781585732","https://openalex.org/W2784465508","https://openalex.org/W2785529341","https://openalex.org/W2785738552","https://openalex.org/W2786036274","https://openalex.org/W2786928559","https://openalex.org/W2787066086","https://openalex.org/W2788084076","https://openalex.org/W2788146012","https://openalex.org/W2788781499","https://openalex.org/W2788842776","https://openalex.org/W2788862220","https://openalex.org/W2793745738","https://openalex.org/W2798705390","https://openalex.org/W2803308811","https://openalex.org/W2803543472","https://openalex.org/W2804791273","https://openalex.org/W2805762288","https://openalex.org/W2809013025","https://openalex.org/W2810754397","https://openalex.org/W2810785043","https://openalex.org/W2883073920","https://openalex.org/W2890803796","https://openalex.org/W2891217993","https://openalex.org/W2892110489","https://openalex.org/W2898621204","https://openalex.org/W2900994167","https://openalex.org/W2902572901","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2904861519","https://openalex.org/W2911618937","https://openalex.org/W2926366943","https://openalex.org/W2942608247","https://openalex.org/W2945586853","https://openalex.org/W2946088105","https://openalex.org/W2947150733","https://openalex.org/W2948175577","https://openalex.org/W2949963197","https://openalex.org/W2950004691","https://openalex.org/W2950037719","https://openalex.org/W2950268955","https://openalex.org/W2950300520","https://openalex.org/W2950872548","https://openalex.org/W2951520685","https://openalex.org/W2951775809","https://openalex.org/W2953981431","https://openalex.org/W2958416396","https://openalex.org/W2962938178","https://openalex.org/W2962957031","https://openalex.org/W2963293747","https://openalex.org/W2963376229","https://openalex.org/W2963423916","https://openalex.org/W2963468355","https://openalex.org/W2963704132","https://openalex.org/W2964093801","https://openalex.org/W2964118020","https://openalex.org/W2964161785","https://openalex.org/W2964179661","https://openalex.org/W2964227312","https://openalex.org/W2964340170","https://openalex.org/W2967210407","https://openalex.org/W2967355195","https://openalex.org/W2971262355","https://openalex.org/W2971413157","https://openalex.org/W2972561734","https://openalex.org/W2975909688","https://openalex.org/W2976223390","https://openalex.org/W2978455699","https://openalex.org/W2982041329","https://openalex.org/W2987973365","https://openalex.org/W2989847975","https://openalex.org/W2990032740","https://openalex.org/W2990747716","https://openalex.org/W2991355586","https://openalex.org/W2995706821","https://openalex.org/W2997273686","https://openalex.org/W3004815632","https://openalex.org/W3007369745","https://openalex.org/W3022566517","https://openalex.org/W3024539867","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3032773894","https://openalex.org/W3035429611","https://openalex.org/W3037440645","https://openalex.org/W3040490156","https://openalex.org/W3041244724","https://openalex.org/W3048825312","https://openalex.org/W3080734044","https://openalex.org/W3093334694","https://openalex.org/W3094028496","https://openalex.org/W3098133181","https://openalex.org/W3101442004","https://openalex.org/W3103262232","https://openalex.org/W3104173699","https://openalex.org/W3105140685","https://openalex.org/W3118210634","https://openalex.org/W4285719527","https://openalex.org/W4291162438","https://openalex.org/W4394672593","https://openalex.org/W6607768588","https://openalex.org/W6616173779","https://openalex.org/W6637587255","https://openalex.org/W6675999342","https://openalex.org/W6677737365","https://openalex.org/W6677916085","https://openalex.org/W6677916933","https://openalex.org/W6682849425","https://openalex.org/W6685029077","https://openalex.org/W6693502484","https://openalex.org/W6695011786","https://openalex.org/W6712047549","https://openalex.org/W6713492654","https://openalex.org/W6734629363","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6743368274","https://openalex.org/W6747387971","https://openalex.org/W6747790125","https://openalex.org/W6747924173","https://openalex.org/W6748554570","https://openalex.org/W6750134565","https://openalex.org/W6751725685","https://openalex.org/W6756256016","https://openalex.org/W6756405035","https://openalex.org/W6759111761","https://openalex.org/W6766900654","https://openalex.org/W6767084887","https://openalex.org/W6767997047","https://openalex.org/W6777656069","https://openalex.org/W6780159193","https://openalex.org/W6782145165"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2768698792","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":69},{"year":2025,"cited_by_count":176},{"year":2024,"cited_by_count":140},{"year":2023,"cited_by_count":100},{"year":2022,"cited_by_count":71},{"year":2021,"cited_by_count":14}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}