{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007544464,0.0004071526,0.0003468185,0.0004330594,0.0006714396,0.0006484935,0.001664196,0.000260788,0.00003171905],"category_scores_gemma":[0.0002852887,0.0004124041,0.0001641535,0.0008248807,0.0001763937,0.001129446,0.0008372888,0.0007530932,0.000168087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000420956,"about_ca_system_score_gemma":0.0003117672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000577756,"about_ca_topic_score_gemma":0.00008440518,"domain_scores_codex":[0.9969586,0.0002139736,0.0005132593,0.0007055965,0.0006346736,0.0009739583],"domain_scores_gemma":[0.9976655,0.0001336008,0.0003047631,0.001248695,0.0003194079,0.0003280238],"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":[0.00001589441,0.00004170801,0.003364125,0.00001218734,0.00003311913,0.00002263657,0.001365068,0.8571754,0.002012925,0.1291606,0.001643902,0.005152518],"study_design_scores_gemma":[0.0002963857,0.0003362331,0.001136912,0.00004951145,0.00001206169,0.00004579526,0.00004694113,0.9860516,0.006765958,0.002684797,0.002117662,0.0004561325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005478566,0.0001013954,0.985467,0.001940242,0.0001990638,0.0004298387,0.000002726306,0.001777631,0.00460356],"genre_scores_gemma":[0.6614044,0.00002998114,0.3314149,0.0021295,0.0001668867,0.0001043583,0.000008323273,0.00004813899,0.004693583],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6559258,"threshold_uncertainty_score":0.9998328,"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."}}