{"id":"https://openalex.org/W2989941899","doi":null,"title":"Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces.","display_name":"Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces.","publication_year":2019,"publication_date":"2019-11-20","ids":{"openalex":"https://openalex.org/W2989941899","mag":"2989941899"},"language":"en","primary_location":{"id":"mag:2989941899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.08756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.08756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101652204","display_name":"Jarom\u00edr Janisch","orcid":"https://orcid.org/0000-0002-4165-6503","observed_orcids":["https://orcid.org/0000-0002-4165-6503"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jarom\u00edr Janisch","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4165-6503","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059337672","display_name":"Tom\u00e1\u0161 Pevn\u00fd","orcid":"https://orcid.org/0000-0002-5768-9713","observed_orcids":["https://orcid.org/0000-0002-5768-9713"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom\u00e1\u0161 Pevn\u00fd","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5768-9713","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049724462","display_name":"Viliam Lis\u00fd","orcid":"https://orcid.org/0000-0002-1647-1507","observed_orcids":["https://orcid.org/0000-0002-1647-1507"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viliam Lis\u00fd","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1647-1507","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.986299991607666,"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":0.986299991607666,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0031999999191612005,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.003000000026077032,"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9779999852180481},{"id":"https://openalex.org/keywords/knowledge-hierarchies","display_name":"knowledge hierarchies","score":0.734000027179718},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.4399999976158142},{"id":"https://openalex.org/keywords/a2c","display_name":"Advantage Actor-Critic","score":0.6669999957084656},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8293536901473999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464475631713867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6986702680587769},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6871951818466187},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5812069773674011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5349166989326477},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5180659294128418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4467426836490631},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33783984184265137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10800245404243469},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2989941899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.08756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2989941899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.08756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W1594297126","https://openalex.org/W2078396547","https://openalex.org/W2121092017","https://openalex.org/W2124125910","https://openalex.org/W2145339207","https://openalex.org/W2260756217","https://openalex.org/W2521075165","https://openalex.org/W2525529746","https://openalex.org/W2624431344","https://openalex.org/W2890680403","https://openalex.org/W2964121744","https://openalex.org/W2964152520","https://openalex.org/W3020831056","https://openalex.org/W3105462378"],"related_works":["https://openalex.org/W6941289825","https://openalex.org/W3201666735","https://openalex.org/W2894389820","https://openalex.org/W7097458101","https://openalex.org/W2612743848","https://openalex.org/W57282082","https://openalex.org/W3098565657","https://openalex.org/W2522609694","https://openalex.org/W3130762189","https://openalex.org/W6894219132"],"abstract_inverted_index":{"We":[0,79,142],"focus":[1],"on":[2,166],"a":[3,16,49,73,81,96,136,147,163],"class":[4],"of":[5,46,61,65,83,149,169],"real-world":[6],"domains,":[7,152],"where":[8,153],"gathering":[9],"hierarchical":[10,107,126],"knowledge":[11,54,88],"is":[12,41,90,132,156],"required":[13],"to":[14,42,51,95,115,157,173],"accomplish":[15],"task.":[17],"Many":[18],"problems":[19],"can":[20,67],"be":[21,68],"represented":[22,92],"in":[23,72,85,146],"this":[24],"manner,":[25],"such":[26],"as":[27,101],"network":[28],"penetration":[29],"testing,":[30],"targeted":[31],"advertising":[32],"or":[33],"medical":[34],"diagnosis.":[35],"In":[36],"our":[37,176],"formalization,":[38],"the":[39,53,62,87,106,118,144,154,159,167],"task":[40,155],"sequentially":[43],"request":[44],"pieces":[45,64],"information":[47,66,170],"about":[48],"sample":[50],"build":[52],"hierarchy":[55,89],"and":[56,75,93,114],"terminate":[57],"when":[58],"suitable.":[59],"Any":[60],"learned":[63],"further":[69],"analyzed,":[70],"resulting":[71],"complex":[74,119],"variable":[76],"action":[77,120],"space.":[78],"present":[80],"combination":[82],"techniques":[84],"which":[86],"explicitly":[91],"given":[94],"deep":[97,138],"reinforcement":[98,139],"learning":[99,140],"algorithm":[100],"its":[102],"input.":[103],"To":[104],"process":[105],"input,":[108],"we":[109,122],"employ":[110],"Hierarchical":[111],"Multiple-Instance":[112],"Learning":[113],"cope":[116],"with":[117,125,134,162],"space,":[121],"factor":[123],"it":[124],"softmax.":[127],"Our":[128],"end-to-end":[129],"differentiable":[130],"model":[131],"trained":[133],"A2C,":[135],"standard":[137],"algorithm.":[141],"demonstrate":[143],"method":[145,177],"set":[148,164],"seven":[150],"classification":[151],"achieve":[158],"best":[160],"accuracy":[161],"budget":[165],"amount":[168],"retrieved.":[171],"Compared":[172],"baseline":[174],"algorithms,":[175],"achieves":[178],"not":[179],"only":[180],"better":[181,185],"results,":[182],"but":[183],"also":[184],"generalization.":[186]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-12-05T00:00:00"}