{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001421382,0.0006289579,0.0006181485,0.0004098403,0.0003395733,0.0009495034,0.00113365,0.0009668216,0.004933543],"category_scores_gemma":[0.006894765,0.0003540804,0.0007969186,0.0006440203,0.001510717,0.001817349,0.001516223,0.001497941,0.0005018036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007408077,"about_ca_system_score_gemma":0.0009157991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002943908,"about_ca_topic_score_gemma":0.00300055,"domain_scores_codex":[0.999011,0.0004585166,0.00006364371,0.0001523538,0.0002278804,0.00008659168],"domain_scores_gemma":[0.9980077,0.001292896,0.0002082039,0.0002266799,0.0001832053,0.00008130475],"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":[0.0001884639,0.00003086262,0.0006990893,0.0000926806,0.00004167923,0.000147284,0.000166334,0.7488874,0.001854038,0.2022433,0.0009990125,0.04464979],"study_design_scores_gemma":[0.00001592616,0.00003805435,0.00006596866,0.00001741327,0.000005772793,0.00002957188,0.00001262119,0.9171605,0.0008081662,0.0805403,0.001296722,0.000008995833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008816935,0.0001035752,0.9891423,0.0001019147,0.00002406482,0.00002184915,0.00004238785,0.0001696842,0.001577327],"genre_scores_gemma":[0.5288681,0.0002138847,0.4667723,0.0001196301,0.00003636705,0.0002128592,0.0001523097,0.0001178235,0.003506676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004933543,"threshold_uncertainty_score":0.01650435,"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."}}