{"id":"https://openalex.org/W4384069847","doi":"https://doi.org/10.1145/3607198","title":"DSMC Evaluation Stages: Fostering Robust and Safe Behavior in Deep Reinforcement Learning \u2013 Extended Version","display_name":"DSMC Evaluation Stages: Fostering Robust and Safe Behavior in Deep Reinforcement Learning \u2013 Extended Version","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384069847","doi":"https://doi.org/10.1145/3607198"},"language":"en","primary_location":{"id":"doi:10.1145/3607198","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607198","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033310691","display_name":"Timo P. Gros","orcid":"https://orcid.org/0000-0002-1100-1952"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo P. Gros","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1100-1952","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043548159","display_name":"Joschka Gro\u00df","orcid":"https://orcid.org/0000-0002-8957-8807"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joschka Gro\u00df","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8957-8807","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065705708","display_name":"Daniel H\u00f6ller","orcid":"https://orcid.org/0000-0002-2776-9288"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel H\u00f6ller","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2776-9288","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076532681","display_name":"J\u00f6rg Hoffmann","orcid":"https://orcid.org/0000-0003-1590-5876"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Hoffmann","raw_affiliation_strings":["Saarland University and German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1590-5876","affiliations":[{"raw_affiliation_string":"Saarland University and German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023667141","display_name":"Michaela Klauck","orcid":"https://orcid.org/0000-0002-6353-227X"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michaela Klauck","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6353-227X","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056099151","display_name":"Hendrik Meerkamp","orcid":"https://orcid.org/0009-0002-4974-6607"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hendrik Meerkamp","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0009-0002-4974-6607","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090443322","display_name":"N. M\u00fcller","orcid":"https://orcid.org/0000-0002-5932-3395"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicola J. M\u00fcller","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5932-3395","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061069077","display_name":"Lukas Schaller","orcid":"https://orcid.org/0009-0007-5937-9448"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Schaller","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0009-0007-5937-9448","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089228948","display_name":"Verena Wolf","orcid":"https://orcid.org/0000-0001-8460-6007"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Verena Wolf","raw_affiliation_strings":["Saarland University and German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8460-6007","affiliations":[{"raw_affiliation_string":"Saarland University and German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7664,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76675874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":"4","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9850999712944031,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9818999767303467,"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":0.7974932193756104},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.708577036857605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953307390213013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6385749578475952},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6207134127616882},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5621846914291382},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4919833838939667},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46730709075927734},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.32429540157318115},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.29008686542510986},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.21170344948768616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09571573138237}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7974932193756104},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.708577036857605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953307390213013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6385749578475952},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6207134127616882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5621846914291382},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4919833838939667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46730709075927734},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.32429540157318115},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.29008686542510986},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.21170344948768616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09571573138237},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":2,"locations":[{"id":"doi:10.1145/3607198","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607198","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},{"id":"doi:10.22028/d291-47754","is_oa":true,"landing_page_url":"https://doi.org/10.22028/d291-47754","pdf_url":null,"source":{"id":"https://openalex.org/S4377196499","display_name":"Publications of the UdS (Saarland University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I91712215","host_organization_name":"Saarland University","host_organization_lineage":["https://openalex.org/I91712215"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.1145/3607198","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607198","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607198","source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G3032849772","display_name":null,"funder_award_id":"TRR 248","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G890954746","display_name":"TRR 248: Grundlagen verst\u00e4ndlicher SoftwareSysteme  f\u00fcr eine nachvollziehbare cyberphysische Welt","funder_award_id":"389792660","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384069847.pdf","grobid_xml":"https://content.openalex.org/works/W4384069847.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1987725948","https://openalex.org/W2098152875","https://openalex.org/W2145339207","https://openalex.org/W2157174816","https://openalex.org/W2160815625","https://openalex.org/W2222789563","https://openalex.org/W2257979135","https://openalex.org/W2334782222","https://openalex.org/W2525579820","https://openalex.org/W2583993537","https://openalex.org/W2601715878","https://openalex.org/W2614801269","https://openalex.org/W2766447205","https://openalex.org/W2798588334","https://openalex.org/W2902332709","https://openalex.org/W2902907165","https://openalex.org/W2951799221","https://openalex.org/W2954360742","https://openalex.org/W2960567166","https://openalex.org/W2962295100","https://openalex.org/W2964067469","https://openalex.org/W2972093249","https://openalex.org/W2980897231","https://openalex.org/W2982316857","https://openalex.org/W2994240296","https://openalex.org/W2996110979","https://openalex.org/W3006773485","https://openalex.org/W3035170447","https://openalex.org/W3080598349","https://openalex.org/W3096351713","https://openalex.org/W3100944043","https://openalex.org/W3149322120","https://openalex.org/W3194575292","https://openalex.org/W3211723445","https://openalex.org/W3214479933","https://openalex.org/W4212774754","https://openalex.org/W4288118072","https://openalex.org/W4297816725","https://openalex.org/W4298857966","https://openalex.org/W4311354561","https://openalex.org/W6637967152","https://openalex.org/W6756303580","https://openalex.org/W6768844577","https://openalex.org/W6771522568"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"(NN)":[2],"are":[3],"gaining":[4],"importance":[5],"in":[6,13,18,22,39,114,193],"sequential":[7],"decision-making.":[8],"Deep":[9],"reinforcement":[10],"learning":[11,19],"(DRL),":[12],"particular,":[14],"is":[15,33,167,187],"extremely":[16],"successful":[17],"action":[20],"policies":[21,113],"complex":[23],"and":[24,56,150,208],"dynamic":[25],"environments.":[26],"Despite":[27],"this":[28],"success,":[29],"however,":[30],"DRL":[31,73,137,146],"technology":[32],"not":[34],"without":[35,180],"its":[36],"failures,":[37],"especially":[38],"safety-critical":[40],"applications:":[41],"(i)":[42,144,207],"the":[43,135,142,168,194],"training":[44,138],"objective":[45],"maximizes":[46],"average":[47],"rewards,":[48],"which":[49,110],"may":[50],"disregard":[51],"rare":[52],"but":[53],"critical":[54,148],"situations":[55,149],"hence":[57],"lack":[58],"local":[59],"robustness;":[60],"(ii)":[61,151],"optimization":[62],"objectives":[63],"targeting":[64],"safety":[65],"typically":[66],"yield":[67],"degenerated":[68],"reward":[69],"structures,":[70],"which,":[71],"for":[72],"to":[74,90,125,153],"work,":[75],"must":[76],"be":[77],"replaced":[78],"with":[79,130],"proxy":[80],"objectives.":[81,156],"Here,":[82],"we":[83],"introduce":[84],"a":[85,178,183,189],"methodology":[86],"that":[87,175,200],"can":[88,203],"help":[89],"address":[91],"both":[92,206],"deficiencies.":[93],"We":[94,133,157],"incorporate":[95],"evaluation":[96],"stages":[97],"(ES)":[98],"into":[99,182],"DRL,":[100],"leveraging":[101],"recent":[102],"work":[103],"on":[104,141,147,161],"deep":[105],"statistical":[106],"model":[107],"checking":[108],"(DSMC),":[109],"verifies":[111],"NN":[112],"Markov":[115],"decision":[116],"processes.":[117],"Our":[118,197],"ES":[119,202],"apply":[120],"DSMC":[121],"at":[122],"regular":[123],"intervals":[124],"determine":[126],"state":[127],"space":[128],"regions":[129],"weak":[131],"performance.":[132],"adapt":[134],"subsequent":[136],"priorities":[139],"based":[140],"outcome,":[143],"focusing":[145],"allowing":[152],"foster":[154],"arbitrary":[155],"run":[158],"case":[159],"studies":[160],"two":[162],"benchmarks.":[163],"One":[164],"of":[165,172],"them":[166],"Racetrack,":[169],"an":[170],"abstraction":[171],"autonomous":[173],"driving":[174],"requires":[176],"navigating":[177],"map":[179],"crashing":[181],"wall.":[184],"The":[185],"other":[186],"MiniGrid,":[188],"widely":[190],"used":[191],"benchmark":[192],"AI":[195],"community.":[196],"results":[198],"show":[199],"DSMC-based":[201],"significantly":[204],"improve":[205],"(ii).":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}