{"id":"W2767354950","doi":"10.1609/aaai.v32i1.11740","title":"Learning With Options That Terminate Off-Policy","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":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dilemma; Flexibility (engineering); Computer science; Odds; Decoupling (probability); Set (abstract data type); Quality (philosophy); Task (project management); Reinforcement learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007368085,0.0005456244,0.0005218051,0.000414434,0.0004396657,0.0009923832,0.005082436,0.0003023357,0.00006177164],"category_scores_gemma":[0.0006581746,0.0003969809,0.0002067307,0.0007827334,0.0007774841,0.0004494975,0.003203654,0.001609792,0.0001785267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001608187,"about_ca_system_score_gemma":0.000563489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007003221,"about_ca_topic_score_gemma":0.000005577178,"domain_scores_codex":[0.9965761,0.00004833548,0.0007042829,0.0009864842,0.00105885,0.0006258874],"domain_scores_gemma":[0.9962533,0.0001196568,0.001370828,0.0008168916,0.001293061,0.0001462843],"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":[0.00008627302,0.0001307447,0.0009257648,0.0002912328,0.0001081065,0.000002493985,0.004523757,0.1144875,0.001945681,0.8203344,0.000233327,0.05693074],"study_design_scores_gemma":[0.00004881916,0.0009228406,0.00040179,0.00222793,0.00006123115,0.00001812703,0.0006152476,0.759514,0.1435865,0.09104863,0.0006886158,0.0008663436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082753,0.00006885009,0.7844772,0.01178554,0.002135181,0.002373097,0.00001168016,0.0009096369,0.08996349],"genre_scores_gemma":[0.9850879,0.0001971974,0.01166441,0.0001608974,0.0002458176,0.00006515523,0.000002286085,0.00004008898,0.002536261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8768126,"threshold_uncertainty_score":0.9998482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08436074975531656,"score_gpt":0.3127829237718858,"score_spread":0.2284221740165693,"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."}}