{"id":"W2963134677","doi":"10.1609/aaai.v32i1.11740","title":"Learning With Options That Terminate Off-Policy","year":2018,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Dilemma; Flexibility (engineering); Odds; Set (abstract data type); Decoupling (probability); Quality (philosophy); Reinforcement learning; Task (project management); Mathematical optimization; Artificial intelligence; Economics; Mathematics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004145728,0.001038541,0.001329646,0.0004995462,0.0005681119,0.001558613,0.001866871,0.002414615,0.004076103],"category_scores_gemma":[0.02122725,0.0004673287,0.0008566705,0.0004914601,0.00216658,0.003906328,0.002040676,0.003641612,0.00061266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382103,"about_ca_system_score_gemma":0.001979471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001169515,"about_ca_topic_score_gemma":0.001482545,"domain_scores_codex":[0.9985171,0.0005779846,0.00009724179,0.0003480157,0.0002506965,0.0002089193],"domain_scores_gemma":[0.9899552,0.007287423,0.0006760645,0.001094534,0.0005539606,0.000432862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004930188,0.0003078952,0.005036423,0.0001778443,0.00008043194,0.000244624,0.0003025456,0.6242405,0.002536299,0.2292741,0.002880458,0.1344258],"study_design_scores_gemma":[0.00003386096,0.00008108085,0.0001449884,0.00003158944,0.00001092657,0.00003289581,0.00002116416,0.9169704,0.0009800362,0.08095681,0.000725689,0.0000104739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06851199,0.0002049836,0.9239619,0.0007367221,0.00006580009,0.0001186085,0.000073722,0.0005373356,0.005788883],"genre_scores_gemma":[0.7606868,0.00020563,0.2310478,0.0004623832,0.00007373404,0.0003055641,0.0002654336,0.0002162752,0.006736376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004145728,"threshold_uncertainty_score":0.02192497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09528522548544098,"score_gpt":0.4151313772490284,"score_spread":0.3198461517635874,"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."}}