{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001640665,0.0001376913,0.0001393198,0.00008335372,0.0001361194,0.0001652672,0.0006409397,0.00004492863,0.0001226042],"category_scores_gemma":[0.00006329962,0.000125036,0.00006793965,0.0002210601,0.00003557475,0.0004100074,0.0002149213,0.0001907146,0.0003029177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007627976,"about_ca_system_score_gemma":0.00001156374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003510169,"about_ca_topic_score_gemma":0.000001406284,"domain_scores_codex":[0.9987355,0.00004887511,0.0001939867,0.0003226894,0.0002975038,0.0004013836],"domain_scores_gemma":[0.9992914,0.00008126002,0.00005071715,0.0003935398,0.00007167557,0.0001114172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001118075,0.00005060634,0.00002856022,0.00000438612,0.00003076312,0.0000328945,0.0005350682,0.004021794,0.0001559018,0.1202942,0.0004906758,0.874354],"study_design_scores_gemma":[0.0003929663,0.0001057867,0.00003843375,0.000005831274,0.000003656229,0.00001045382,0.00002103068,0.9926615,0.00004804506,0.0005693585,0.005979246,0.0001637401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001625509,0.00007519979,0.978272,0.0006196293,0.0001505511,0.0001589181,1.442405e-7,0.0005192202,0.02004174],"genre_scores_gemma":[0.8744354,0.000006914153,0.1127972,0.0003583977,0.00004524921,0.00002641509,0.000001136074,0.000008618325,0.01232064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9886397,"threshold_uncertainty_score":0.5098822,"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."}}