{"id":"https://openalex.org/W4205472340","doi":"https://doi.org/10.1145/3493700.3493709","title":"Identifying efficient curricula for reinforcement learning in complex environments with a fixed computational budget","display_name":"Identifying efficient curricula for reinforcement learning in complex environments with a fixed computational budget","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4205472340","doi":"https://doi.org/10.1145/3493700.3493709"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.11762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068372952","display_name":"Omkar Shelke","orcid":"https://orcid.org/0000-0003-2767-8607"},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Omkar Shelke","raw_affiliation_strings":["TCS Research, IN"],"affiliations":[{"raw_affiliation_string":"TCS Research, IN","institution_ids":["https://openalex.org/I4210104194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455101","display_name":"Hardik Meisheri","orcid":"https://orcid.org/0000-0002-9014-1098"},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hardik Meisheri","raw_affiliation_strings":["TCS Research, IN"],"affiliations":[{"raw_affiliation_string":"TCS Research, IN","institution_ids":["https://openalex.org/I4210104194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045214135","display_name":"Harshad Khadilkar","orcid":"https://orcid.org/0000-0003-3601-778X"},"institutions":[{"id":"https://openalex.org/I4210104194","display_name":"Tennessee Cancer Specialists","ror":"https://ror.org/01krbfc31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210104194"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harshad Khadilkar","raw_affiliation_strings":["TCS Research, IN"],"affiliations":[{"raw_affiliation_string":"TCS Research, IN","institution_ids":["https://openalex.org/I4210104194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068372952"],"corresponding_institution_ids":["https://openalex.org/I4210104194"],"apc_list":null,"apc_paid":null,"fwci":0.138,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50667171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983000159263611,"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/T10260","display_name":"Software Engineering Research","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8466618061065674},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7582124471664429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724969744682312},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5538218021392822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541553258895874},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5166592597961426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49643999338150024},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.49537765979766846},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48073315620422363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43432915210723877},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4260888397693634},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42141228914260864},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22990700602531433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09980884194374084}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8466618061065674},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7582124471664429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724969744682312},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5538218021392822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541553258895874},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5166592597961426},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49643999338150024},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.49537765979766846},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48073315620422363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43432915210723877},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4260888397693634},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42141228914260864},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22990700602531433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09980884194374084},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3493700.3493709","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.11762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11762","pdf_url":"https://arxiv.org/pdf/2102.11762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.11762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11762","pdf_url":"https://arxiv.org/pdf/2102.11762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1777239053","https://openalex.org/W1931877416","https://openalex.org/W2065356613","https://openalex.org/W2107544712","https://openalex.org/W2137647991","https://openalex.org/W2158349948","https://openalex.org/W2168359464","https://openalex.org/W2174803659","https://openalex.org/W2396217537","https://openalex.org/W2409942531","https://openalex.org/W2522489477","https://openalex.org/W2604173613","https://openalex.org/W2736601468","https://openalex.org/W2788862220","https://openalex.org/W2796290181","https://openalex.org/W2810298113","https://openalex.org/W2889698555","https://openalex.org/W2904616874","https://openalex.org/W2916722070","https://openalex.org/W2943197047","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2965908679","https://openalex.org/W2986185262","https://openalex.org/W3104515094","https://openalex.org/W4287620130","https://openalex.org/W4300198501"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W4320018150","https://openalex.org/W2040808657","https://openalex.org/W4239582170","https://openalex.org/W2918664383","https://openalex.org/W3123119822","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Pommerman":[0],"is":[1,101,159],"a":[2,31,46,50,56,65,72,135],"hybrid":[3],"cooperative/adversarial":[4],"multi-agent":[5],"environment,":[6],"with":[7,89,114],"challenging":[8,32],"characteristics":[9],"in":[10,55,160,165],"terms":[11],"of":[12,60,106,168,191,197],"partial":[13],"observability,":[14],"limited":[15],"or":[16],"no":[17],"communication,":[18],"sparse":[19],"and":[20,23,52,94,104,117,151,199],"delayed":[21],"rewards,":[22],"restrictive":[24],"inference":[25],"time":[26],"limits.":[27],"This":[28],"makes":[29],"it":[30,158],"environment":[33,195],"for":[34,48],"reinforcement":[35],"learning":[36,49],"(RL)":[37],"approaches.":[38],"In":[39],"this":[40,149],"paper,":[41],"we":[42,187],"focus":[43],"on":[44,203],"developing":[45],"curriculum":[47],"robust":[51,131],"promising":[53],"policy":[54,68,83],"constrained":[57,155],"computational":[58,156],"budget":[59],"100,000":[61],"games,":[62],"starting":[63,79],"from":[64,80,144,178],"fixed":[66],"base":[67,82,194],"(which":[69],"itself":[70],"imitates":[71],"noisy":[73],"expert":[74],"policy).":[75],"All":[76],"RL":[77],"algorithms":[78],"the":[81,90,95,102,121,145,166,179,189,193,204],"use":[84],"vanilla":[85],"proximal-policy":[86],"optimization":[87],"(PPO)":[88],"same":[91],"reward":[92],"function,":[93],"only":[96],"difference":[97],"between":[98],"their":[99],"training":[100,113],"mix":[103],"sequence":[105],"opponent":[107,122,140,175],"policies.":[108],"One":[109],"expects":[110],"that":[111,153],"beginning":[112],"simpler":[115],"opponents":[116],"then":[118],"gradually":[119],"increasing":[120],"difficulty":[123],"will":[124],"facilitate":[125],"faster":[126],"learning,":[127],"leading":[128],"to":[129,163],"more":[130],"policies":[132,141,176],"compared":[133],"against":[134,172],"baseline":[136],"where":[137,186],"all":[138,173],"available":[139,174],"are":[142],"introduced":[143],"start.":[146,180],"We":[147,181],"test":[148],"hypothesis":[150],"show":[152],"within":[154],"budgets,":[157],"fact":[161],"better":[162],"\u201clearn":[164],"school":[167],"hard":[169],"knocks\u201d,":[170],"i.e.,":[171],"nearly":[177],"also":[182],"include":[183],"ablation":[184],"studies":[185],"study":[188],"effect":[190],"modifying":[192],"properties":[196],"ammo":[198],"bomb":[200],"blast":[201],"strength":[202],"agent":[205],"performance.":[206]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-01-26T00:00:00"}