{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008671142,0.0004692763,0.000421866,0.0002347775,0.0006097288,0.001540615,0.003208916,0.0002880064,0.0001211561],"category_scores_gemma":[0.0003780056,0.0003732643,0.0001434389,0.0004289993,0.0004128819,0.0008869634,0.001511606,0.001363952,0.000124666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001409923,"about_ca_system_score_gemma":0.0003264886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006138556,"about_ca_topic_score_gemma":0.00001098173,"domain_scores_codex":[0.9965002,0.00005936492,0.0008669427,0.001037911,0.001043863,0.0004917292],"domain_scores_gemma":[0.9955813,0.00009027215,0.0012935,0.0006882527,0.002198275,0.0001483449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001089411,0.000117576,0.0002355814,0.0001557946,0.00006817714,9.061487e-7,0.008787661,0.2578963,0.004465611,0.6824998,0.0001614932,0.04550213],"study_design_scores_gemma":[0.00003025495,0.0004773075,0.0000561635,0.0008472863,0.00003594178,0.000006907107,0.0004372246,0.8798712,0.0885994,0.02902795,0.000193755,0.000416607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05731665,0.000008991417,0.9303127,0.004541708,0.0006322532,0.001081788,0.000005283614,0.0003070952,0.005793556],"genre_scores_gemma":[0.9504156,0.00004602099,0.04798674,0.0003582119,0.0002666632,0.00009701472,0.000007020346,0.00003618588,0.0007865921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8930989,"threshold_uncertainty_score":0.9998719,"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."}}