{"id":"W2963250930","doi":"","title":"Convergent Tree Backup and Retrace with Function Approximation","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Backup; Reinforcement learning; Saddle point; Computer science; Tree (set theory); Function approximation; Mathematical optimization; Convergence (economics); Function (biology); Approximation algorithm; Bootstrapping (finance); Saddle; Quadratic equation; Applied mathematics; Mathematics; Algorithm; Artificial intelligence; Combinatorics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002661716,0.0001517535,0.0001076382,0.0001510512,0.0001775019,0.0003051517,0.0003938457,0.00005105791,0.000317947],"category_scores_gemma":[0.0001030053,0.0001287282,0.00002152213,0.0001452818,0.00008724393,0.0004743327,0.0001310629,0.0003472686,0.0001695954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005269845,"about_ca_system_score_gemma":0.00003866876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002570048,"about_ca_topic_score_gemma":0.00001647724,"domain_scores_codex":[0.9987202,0.00007861716,0.0001898734,0.0003579354,0.000483292,0.0001701357],"domain_scores_gemma":[0.9991977,0.00005898992,0.0001828725,0.000201704,0.0002919262,0.00006687491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003084109,0.00005826685,0.03198981,0.00002267352,0.0001416957,0.00001252279,0.001383404,0.05123719,0.003051647,0.8328292,0.0002338331,0.07873134],"study_design_scores_gemma":[0.000486737,0.0008404995,0.008655562,0.00005467083,0.000006196357,0.00001628999,0.00004624257,0.9833678,0.000293576,0.0007184054,0.005348602,0.0001653896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0154634,0.000008837257,0.9304999,0.001709621,0.0004435267,0.0001066829,5.727314e-7,0.0001673982,0.0516001],"genre_scores_gemma":[0.9806107,0.00002055241,0.01535107,0.0002774756,0.0001329859,0.000007852477,0.00002187747,0.00001126028,0.00356618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9651474,"threshold_uncertainty_score":0.5249385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275852956681716,"score_gpt":0.265515831660857,"score_spread":0.2379305359926854,"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."}}