{"id":"W2754203286","doi":"10.1609/aaai.v32i1.11831","title":"When Waiting Is Not an Option: Learning Options With a Deliberation Cost","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"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; Management science; Risk analysis (engineering); Artificial intelligence; Epistemology; Economics; Business; Political science","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":[0.003254501,0.0007663326,0.0009888601,0.0003715327,0.0005243709,0.001386717,0.001623767,0.001891857,0.003441066],"category_scores_gemma":[0.02294508,0.00056125,0.000630928,0.0003994105,0.002426793,0.005068857,0.002580186,0.003169828,0.0003804048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061779,"about_ca_system_score_gemma":0.001643582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002402143,"about_ca_topic_score_gemma":0.002464376,"domain_scores_codex":[0.998332,0.0007454714,0.00008714649,0.0004116982,0.0002340416,0.0001896312],"domain_scores_gemma":[0.9879401,0.009330926,0.0008614725,0.0007955384,0.0004460009,0.0006259366],"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":[0.001238223,0.0002388884,0.004165752,0.0002350649,0.0001393154,0.0004353267,0.0005953477,0.6957597,0.002742938,0.1920546,0.002102515,0.1002922],"study_design_scores_gemma":[0.00007075149,0.00008455709,0.0002917899,0.00002561006,0.00002294847,0.00005044846,0.000056823,0.821645,0.00110968,0.1759407,0.0006785549,0.0000230386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1491085,0.0003542252,0.8421383,0.001786729,0.00006747895,0.0000872173,0.0001191738,0.0005966439,0.005741761],"genre_scores_gemma":[0.8886179,0.0001692233,0.1079875,0.0002477951,0.00003405664,0.0001154345,0.0001226586,0.0001066261,0.00259878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003441066,"threshold_uncertainty_score":0.01721168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1238861233389877,"score_gpt":0.3176455879313191,"score_spread":0.1937594645923314,"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."}}