{"id":"W2890960027","doi":"","title":"Iterative Value-Aware Model Learning","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Reinforcement learning; Computer science; Contrast (vision); Class (philosophy); Mathematical optimization; Artificial intelligence; Value (mathematics); Iterative learning control; Iterative method; Optimization problem; Decision problem; Machine learning; Algorithm; Mathematics; Control (management)","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":[0.002061944,0.001191698,0.001548833,0.0005377662,0.0005091616,0.001372824,0.002272788,0.001535945,0.00298721],"category_scores_gemma":[0.01029317,0.0007849041,0.000815039,0.000565819,0.001558294,0.00218849,0.003005421,0.002664538,0.0005542154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001431091,"about_ca_system_score_gemma":0.002188389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00329309,"about_ca_topic_score_gemma":0.003310183,"domain_scores_codex":[0.9983145,0.0006559777,0.00006335948,0.0003210047,0.0004343029,0.0002109561],"domain_scores_gemma":[0.9948791,0.003681539,0.0003372892,0.0005158139,0.0004220591,0.0001641358],"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":[0.00008489956,0.00007035461,0.0006110391,0.00009448225,0.00004539478,0.00007712821,0.0001199956,0.87802,0.0009589668,0.05985911,0.001558156,0.0585005],"study_design_scores_gemma":[0.000007209645,0.00001726959,0.00002345676,0.000005857946,0.000003542204,0.00001235484,0.000004904847,0.9806629,0.0002722975,0.01864684,0.0003400855,0.000003223283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005705336,0.0001115863,0.991682,0.0001598247,0.00001460545,0.00002906866,0.00001911425,0.0003017735,0.001976736],"genre_scores_gemma":[0.7090731,0.0002283454,0.2859787,0.0002619712,0.00004966781,0.0002720086,0.0001865486,0.0001853588,0.003764282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00329309,"threshold_uncertainty_score":0.01090473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437263597373432,"score_gpt":0.2467520311628098,"score_spread":0.2323793951890755,"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."}}