{"id":"W2963142324","doi":"10.1609/aaai.v32i1.11831","title":"When Waiting Is Not an Option: Learning Options With a Deliberation Cost","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Deliberation; Interpretability; Bounded rationality; Computer science; Rationality; Work (physics); Management science; Risk analysis (engineering); Artificial intelligence; Epistemology; Economics; Business; Political science; Engineering; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002898371,0.0007419505,0.0009069122,0.0003237512,0.0004744066,0.001175254,0.00148567,0.00161757,0.002877244],"category_scores_gemma":[0.01938633,0.000484217,0.0005839891,0.000343495,0.002269358,0.004393625,0.00233324,0.002812682,0.0003306737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009620072,"about_ca_system_score_gemma":0.001553507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002326082,"about_ca_topic_score_gemma":0.002416314,"domain_scores_codex":[0.9985519,0.0006350838,0.00007941933,0.000355644,0.000208285,0.0001696937],"domain_scores_gemma":[0.9892901,0.008310358,0.0007840408,0.0006753033,0.0003963495,0.0005438957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001211887,0.0002263984,0.003869397,0.0002120657,0.000126545,0.0004065065,0.0005409782,0.7377026,0.003268438,0.1441357,0.001693542,0.106606],"study_design_scores_gemma":[0.00006918348,0.00009668653,0.0002905142,0.00002373243,0.00002325938,0.00004908965,0.00005354647,0.8649562,0.001332723,0.1324665,0.0006160202,0.00002254007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1565981,0.0003110777,0.8356711,0.001416529,0.00006111731,0.00008321868,0.00009438936,0.0006106641,0.005153897],"genre_scores_gemma":[0.8918637,0.0001522866,0.1053035,0.000197644,0.00002784804,0.0001040806,0.00009773239,0.0000875164,0.002165698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002898371,"threshold_uncertainty_score":0.01532823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03604037314581124,"score_gpt":0.274417942026724,"score_spread":0.2383775688809128,"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."}}