{"id":"W3033337213","doi":"10.1145/3401071.3401657","title":"Research challenges in deep reinforcement learning-based join query optimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Query optimization; Computer science; Sargable; Join (topology); Reinforcement learning; Query plan; Query expansion; Web query classification; Web search query; Set (abstract data type); Theoretical computer science; Data mining; Information retrieval; Artificial intelligence; Search engine; Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007213202,0.0008742195,0.002206683,0.0005123609,0.0006906488,0.003172991,0.003166337,0.002162877,0.003447368],"category_scores_gemma":[0.01823253,0.0007477764,0.0008927772,0.001465501,0.001765303,0.00593849,0.001986345,0.004724011,0.0007209099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002438983,"about_ca_system_score_gemma":0.003802904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01285076,"about_ca_topic_score_gemma":0.01030912,"domain_scores_codex":[0.9961193,0.001622145,0.0002847791,0.0007411715,0.0008800266,0.0003526561],"domain_scores_gemma":[0.9854323,0.01107427,0.0004856581,0.001117966,0.001439529,0.0004503106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002635742,0.0004760419,0.002425116,0.0004999955,0.0001269796,0.00007865617,0.0002968031,0.698448,0.001961228,0.054435,0.01023259,0.2307559],"study_design_scores_gemma":[0.00001801827,0.00003502926,0.0001196902,0.00001546094,0.00000735162,0.00001290548,0.00007010969,0.9802929,0.0003984485,0.01716196,0.001860168,0.000008012243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03827844,0.009713983,0.9308334,0.01362242,0.0002662568,0.0001375268,0.0003293139,0.001334927,0.005483726],"genre_scores_gemma":[0.5727627,0.004117401,0.4150721,0.002012684,0.0005504285,0.0002378452,0.0006762784,0.000365786,0.00420471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285076,"threshold_uncertainty_score":0.03814751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1240569034594771,"score_gpt":0.3115986065888434,"score_spread":0.1875417031293664,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}