{"id":"W4405930443","doi":"10.1007/978-3-031-74640-6_18","title":"Learning When to Observe: A Frugal Reinforcement Learning Framework for a High-Cost World","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Innovation and Socioeconomic Development","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Ottawa; Vector Institute; National Research Council Canada","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001278899,0.0002031958,0.0002210892,0.001569841,0.000711075,0.001435875,0.0009165083,0.00009719547,0.0001003402],"category_scores_gemma":[0.000116304,0.000215218,0.00004268077,0.0004412408,0.0001842837,0.003463827,0.001476619,0.0006212611,0.0005296815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002376126,"about_ca_system_score_gemma":0.0001170665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002765144,"about_ca_topic_score_gemma":0.00002572703,"domain_scores_codex":[0.9985632,0.000003926908,0.0007139324,0.0002307181,0.0002531644,0.0002350035],"domain_scores_gemma":[0.9985694,0.0001297789,0.0003404705,0.0004991711,0.0004371185,0.00002411616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004432717,0.000003221248,0.00009577378,0.00007894586,0.000007938863,8.212543e-8,0.001229006,0.003209929,2.315258e-7,0.9429556,0.001339339,0.05107547],"study_design_scores_gemma":[0.0001563605,0.00001048772,0.000379233,0.0003735155,0.000008232911,4.600788e-7,0.0001013445,0.1043895,6.068306e-7,0.04649588,0.8478299,0.0002544411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00036017,0.00007740205,0.3100467,0.0104006,0.001472385,0.001839874,0.000005155122,0.0002749938,0.6755227],"genre_scores_gemma":[0.3744581,0.0005828213,0.3663479,0.05259482,0.001729793,0.001118779,0.001663761,0.0001315218,0.2013725],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8964598,"threshold_uncertainty_score":0.9996007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04815994935224382,"score_gpt":0.2880743671744916,"score_spread":0.2399144178222478,"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."}}