{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002710384,0.001239705,0.002084788,0.0006847101,0.0007663841,0.001159361,0.002460454,0.002092536,0.003938973],"category_scores_gemma":[0.01382367,0.0006008911,0.0008136398,0.0006384702,0.001773831,0.001975424,0.002819892,0.00342328,0.0009254823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248374,"about_ca_system_score_gemma":0.001824748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003130248,"about_ca_topic_score_gemma":0.002609506,"domain_scores_codex":[0.9989777,0.0003407095,0.00004797934,0.0002093151,0.0003003643,0.0001239884],"domain_scores_gemma":[0.9949971,0.003133523,0.0003332614,0.0006610859,0.0005613175,0.0003137157],"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":[0.0002178161,0.0001149966,0.0008011697,0.0001368254,0.0000420695,0.0001411111,0.0001374701,0.8479833,0.001589151,0.05266475,0.003345425,0.09282597],"study_design_scores_gemma":[0.00001526451,0.00003464485,0.00003866708,0.000009706613,0.000003075682,0.0000237251,0.000007728343,0.9866701,0.000517519,0.01227923,0.0003959235,0.000004388615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01416427,0.0002851525,0.9822041,0.0003618729,0.00006469055,0.00006951856,0.00004310397,0.0004676208,0.002339624],"genre_scores_gemma":[0.664749,0.0002454307,0.3271852,0.0004310102,0.00007358113,0.0003327477,0.0002405361,0.0003394242,0.006403112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003938973,"threshold_uncertainty_score":0.01433408,"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."}}