{"id":"W2740174381","doi":"10.24963/ijcai.2017/717","title":"Approximate Value Iteration with Temporally Extended Actions (Extended Abstract)","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Landmark; Convergence (economics); Computer science; Mathematical optimization; Bellman equation; Value (mathematics); Function (biology); State space; Term (time); Algorithm; Mathematics; Artificial intelligence; Machine learning; Statistics; Economics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002565149,0.0001707527,0.00014161,0.00008306353,0.000834926,0.00160939,0.001160932,0.00006382928,0.00005697617],"category_scores_gemma":[0.00006235905,0.000131969,0.00004628814,0.00007906776,0.00007926518,0.002152519,0.0002142637,0.0001929976,0.0001320418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004575937,"about_ca_system_score_gemma":0.00009961055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000575394,"about_ca_topic_score_gemma":0.00001190055,"domain_scores_codex":[0.9986684,0.00002132919,0.0002404478,0.0003753987,0.0004027327,0.0002917021],"domain_scores_gemma":[0.9979372,0.00003442526,0.0003208975,0.001476356,0.0001296098,0.0001015176],"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":[0.00004242444,0.0002008875,0.001810199,0.00005761098,0.0001331071,0.0000788336,0.0009644876,0.3165141,0.003591451,0.6500452,0.002516735,0.02404491],"study_design_scores_gemma":[0.0007660994,0.0002382823,0.0622018,0.00004546334,0.00001471059,0.00004349501,0.0000399467,0.926466,0.003218993,0.00184753,0.004705918,0.0004117791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002253381,0.000002926976,0.9051644,0.001529331,0.0002584909,0.0002228042,4.19849e-7,0.0003177682,0.09025049],"genre_scores_gemma":[0.8248396,0.000004435918,0.1671706,0.000220289,0.00005715565,0.00001767132,0.000006009764,0.00001307541,0.007671162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8225862,"threshold_uncertainty_score":0.999427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03463366844770536,"score_gpt":0.2920029215859134,"score_spread":0.257369253138208,"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."}}