{"id":"W1873139171","doi":"10.1109/ccece.2000.849537","title":"A modified actor-critic reinforcement learning algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Backpropagation; Inverted pendulum; Artificial neural network; Bellman equation; Function (biology); Function approximation; Artificial intelligence; Fuzzy logic; Algorithm; Mathematics; Mathematical optimization; Nonlinear system","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":[0.00102274,0.001086996,0.001337473,0.0004607877,0.0004590063,0.000789281,0.002040872,0.001476443,0.004656529],"category_scores_gemma":[0.001711361,0.0004060448,0.0004571399,0.0003491597,0.0006876886,0.0006745546,0.0008725214,0.001192261,0.001204722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007509685,"about_ca_system_score_gemma":0.001286549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004361044,"about_ca_topic_score_gemma":0.003220951,"domain_scores_codex":[0.9994516,0.000160542,0.00002574575,0.0001048685,0.0001992777,0.00005794192],"domain_scores_gemma":[0.9994763,0.0001974031,0.00004527414,0.00004270711,0.0001926875,0.0000457748],"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":[0.0001225703,0.00006045958,0.000328023,0.00007896553,0.00007155022,0.0001440675,0.00005214188,0.8693155,0.002771113,0.01989758,0.003017068,0.1041408],"study_design_scores_gemma":[0.00002505054,0.00002382585,0.00003022566,0.000003796945,0.000005329607,0.00001493232,0.000001462371,0.9966429,0.0002809559,0.001705288,0.00126156,0.000004663948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004132775,0.0002146143,0.9907709,0.0001505814,0.0001135204,0.00008218369,0.000026353,0.0005972258,0.003911848],"genre_scores_gemma":[0.5365903,0.0003753509,0.4428649,0.0003159141,0.0001466116,0.0005780216,0.0001623076,0.0001697561,0.01879686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004656529,"threshold_uncertainty_score":0.01557761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01959364087753272,"score_gpt":0.2270879000056234,"score_spread":0.2074942591280907,"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."}}