{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000260551,0.0001186379,0.0000896298,0.00008494749,0.0005097354,0.0005561946,0.0004043158,0.00004796933,0.0002279197],"category_scores_gemma":[0.00003229847,0.0001014861,0.00002204168,0.0002256832,0.00006400506,0.001372568,0.0001228282,0.0001761136,0.0003077067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004667035,"about_ca_system_score_gemma":0.00005675307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003144758,"about_ca_topic_score_gemma":0.0000192815,"domain_scores_codex":[0.9988305,0.00006734195,0.0001945141,0.0003260761,0.0003262316,0.0002553528],"domain_scores_gemma":[0.9990908,0.00004125467,0.000103966,0.0003936413,0.0002750923,0.00009524218],"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":[0.00001537442,0.00003137839,0.001453295,0.00000810894,0.00002860656,0.000004968424,0.006161982,0.7682043,0.001184656,0.1821218,0.0009072204,0.03987833],"study_design_scores_gemma":[0.0002246566,0.0004505034,0.0004751726,0.00001897898,0.000005512859,0.00001852785,0.0001144038,0.9877355,0.001687095,0.00009883279,0.009005747,0.0001650717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01233568,0.000002284221,0.9748003,0.001417894,0.0001033022,0.0001571949,1.416929e-7,0.0003891889,0.01079402],"genre_scores_gemma":[0.6502723,0.000002479375,0.3428816,0.0009974121,0.0001734594,0.00001178114,0.000006358484,0.0000108794,0.005643788],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6379365,"threshold_uncertainty_score":0.5363398,"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."}}