{"id":"W3093980962","doi":"","title":"Incremental Policy Gradients for Online Reinforcement Learning Control","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Term (time); Control (management); Artificial intelligence; Econometrics; Machine learning; Economics","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":[0.0002550713,0.0001760153,0.000206317,0.0001344617,0.0002356201,0.0002060425,0.0005635346,0.00005632495,0.00007487219],"category_scores_gemma":[0.0003960844,0.0001713054,0.0001264855,0.0003852242,0.00002772592,0.0003635795,0.0003220808,0.000175105,0.00005168159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001685414,"about_ca_system_score_gemma":0.0002198615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003581424,"about_ca_topic_score_gemma":0.000005709175,"domain_scores_codex":[0.9982815,0.00006245689,0.0003850806,0.0003773695,0.0003960551,0.0004975579],"domain_scores_gemma":[0.998915,0.0001466295,0.0001391379,0.0004480288,0.0002139416,0.0001372809],"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":[0.00001179901,0.00005453821,0.0009916845,0.00002346315,0.000077347,0.00001196945,0.0001807075,0.8638425,0.001638852,0.1243288,0.0007965814,0.008041798],"study_design_scores_gemma":[0.002223456,0.0002909016,0.0006056829,0.00001818647,0.00001271124,0.00001950048,0.0000651437,0.9611456,0.002735662,0.0002736652,0.03236457,0.0002449059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002034498,0.00002354937,0.9893067,0.001631747,0.0002896818,0.0003052549,0.000001569662,0.0002311083,0.006175878],"genre_scores_gemma":[0.8880913,0.00002226412,0.09365478,0.002714625,0.0002113648,0.00002995064,0.00006831945,0.00001838091,0.01518906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8956519,"threshold_uncertainty_score":0.6985633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01937927747768515,"score_gpt":0.280628564126172,"score_spread":0.2612492866484868,"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."}}