{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002095745,0.001272914,0.001140224,0.0004254496,0.0003907899,0.0008706378,0.001360384,0.001461228,0.003032416],"category_scores_gemma":[0.005353895,0.0006177289,0.0006460789,0.0004560518,0.001348142,0.0008851603,0.001013369,0.002699631,0.0006850052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001130788,"about_ca_system_score_gemma":0.001255666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005234078,"about_ca_topic_score_gemma":0.005072001,"domain_scores_codex":[0.9994042,0.0002346152,0.00003189821,0.0001152634,0.0001655959,0.0000484274],"domain_scores_gemma":[0.9981445,0.001283036,0.0001143095,0.0001393685,0.0002612906,0.00005742716],"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":[0.00005019353,0.00003140309,0.0003281649,0.00009744124,0.00004120558,0.00006907418,0.00005438037,0.932126,0.001105016,0.02980837,0.001065175,0.03522356],"study_design_scores_gemma":[0.000005012286,0.000008953005,0.00001824987,0.000004313577,0.000003037503,0.000005740419,0.00000127468,0.9954477,0.0002034846,0.003933962,0.0003654593,0.000002773993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002729315,0.0003739716,0.9944875,0.0001342055,0.0000504233,0.00003014801,0.00001547704,0.0002610091,0.001918021],"genre_scores_gemma":[0.6596587,0.0008231437,0.3271463,0.0002909299,0.0001054662,0.0003801984,0.0001092064,0.0001953567,0.0112907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005234078,"threshold_uncertainty_score":0.01108348,"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."}}