{"id":"W2620853660","doi":"10.5555/3091125.3091207","title":"Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Function approximation; Nonlinear system; Function (biology); Class (philosophy); Artificial intelligence; Temporal difference learning; Mathematical optimization; Machine learning; Artificial neural network; Mathematics","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":[0.0006936602,0.0002544191,0.0003079817,0.0001641078,0.0007158094,0.0007739886,0.0005820224,0.0001180466,0.000004181938],"category_scores_gemma":[0.0002332062,0.0002410812,0.00006871614,0.00007773365,0.00005591044,0.001365982,0.0003209945,0.000200038,0.00002851236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364622,"about_ca_system_score_gemma":0.00003919481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002303363,"about_ca_topic_score_gemma":0.00001289189,"domain_scores_codex":[0.9980228,0.00009896817,0.0005160042,0.0005155409,0.0003923136,0.0004543734],"domain_scores_gemma":[0.998518,0.00007976295,0.0004985808,0.0006020628,0.000173859,0.0001277722],"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":[0.0001343552,0.0001696242,0.01879159,0.0005424324,0.0002547882,0.00001923575,0.003381806,0.9513159,0.0005697796,0.01077828,0.0004754629,0.01356674],"study_design_scores_gemma":[0.002114725,0.0003722293,0.01187954,0.0002672307,0.00002202149,0.000002869716,0.0003278439,0.9791633,0.00005173621,0.00001977584,0.005518189,0.0002605273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01229442,0.00008575003,0.9839391,0.00006000205,0.001187937,0.001753775,0.000002672321,0.00007801624,0.0005983266],"genre_scores_gemma":[0.9859113,0.00007322879,0.01103823,0.00006920133,0.0001131222,0.000227079,0.00003295676,0.00002487665,0.002510067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9736168,"threshold_uncertainty_score":0.9831004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07223075096191683,"score_gpt":0.309418597286914,"score_spread":0.2371878463249972,"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."}}