{"id":"W6891724308","doi":"10.48448/ey03-4n67","title":"A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Backpropagation; Leverage (statistics); Novelty; Key (lock); Markov decision process; Probability distribution; Stochastic optimization; Optimization problem; Reinforcement learning","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":[0.002530778,0.001585927,0.001403798,0.00080444,0.0005742912,0.001544929,0.002034745,0.001545035,0.002990688],"category_scores_gemma":[0.006341848,0.0008344146,0.001075974,0.0007571587,0.001845129,0.002041035,0.003008408,0.002894546,0.0004105549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001875041,"about_ca_system_score_gemma":0.00279367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00581456,"about_ca_topic_score_gemma":0.004922125,"domain_scores_codex":[0.9987198,0.0005086953,0.00007525665,0.000233511,0.000334876,0.0001278918],"domain_scores_gemma":[0.9972225,0.001765039,0.0002511108,0.000221643,0.0003720959,0.0001676803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009953614,0.00001057792,0.0001021589,0.00002350693,0.00001117726,0.00001963173,0.00001821919,0.9754177,0.0002131697,0.01895425,0.0002394903,0.004980067],"study_design_scores_gemma":[0.000002619576,0.00001155149,0.00002172744,0.00000538799,0.000002643636,0.000005973968,0.000003662643,0.9871006,0.0001427822,0.01244623,0.0002535723,0.000003147057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002709052,0.0001184076,0.9957415,0.0001606603,0.00001650597,0.00001624006,0.00003352459,0.0001412713,0.001062936],"genre_scores_gemma":[0.6061782,0.0008183427,0.3859809,0.0003577909,0.0001196203,0.0004145376,0.000297799,0.0004368979,0.005395909],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00581456,"threshold_uncertainty_score":0.01360446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0246026434461901,"score_gpt":0.3260392245394246,"score_spread":0.3014365810932345,"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."}}