{"id":"W6983024021","doi":"","title":"Learning and planning with noise in optimization and reinforcement learning","year":2023,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Maximum likelihood; Structured prediction; Random noise","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002509127,0.001042722,0.001280992,0.000596927,0.0005360431,0.002148821,0.001391767,0.001638292,0.003490183],"category_scores_gemma":[0.01318435,0.000620203,0.0008775896,0.000755406,0.002480755,0.002790107,0.001768875,0.00273362,0.0004997425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001978093,"about_ca_system_score_gemma":0.001734937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006004381,"about_ca_topic_score_gemma":0.005143238,"domain_scores_codex":[0.9980385,0.0009544615,0.00008105571,0.0003839181,0.0003951774,0.000146882],"domain_scores_gemma":[0.9945227,0.004384929,0.0002839084,0.0003430116,0.0003306796,0.000134719],"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":[0.0001479509,0.00005205335,0.0009478304,0.00017995,0.00008745257,0.00008031339,0.0001456721,0.7550339,0.0008595637,0.1812007,0.0013488,0.05991577],"study_design_scores_gemma":[0.00001680892,0.00005570339,0.0001759574,0.00002435033,0.00001287851,0.00001932283,0.0000161967,0.9251733,0.00055119,0.07181445,0.002128229,0.00001151356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01816488,0.002132387,0.9700762,0.001084202,0.0001710876,0.00003524558,0.00005133545,0.0003207337,0.007963902],"genre_scores_gemma":[0.7554199,0.003324351,0.2218512,0.000522167,0.0004920898,0.0002617081,0.0001667398,0.0002543242,0.01770765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006004381,"threshold_uncertainty_score":0.0143522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008767026322164946,"score_gpt":0.2032785240461548,"score_spread":0.1945114977239898,"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."}}