{"id":"W4384574988","doi":"10.23952/jano.5.2023.2.01","title":"Multi-step actor-critic framework for reinforcement learning in continuous control","year":2023,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Sequence (biology); State (computer science); Control (management); Artificial intelligence; Reinforcement; Optimal control; Action (physics); Machine learning; Mathematical optimization; Mathematics; Algorithm; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001118395,0.001231492,0.001170201,0.0003613631,0.0003628323,0.0009034041,0.001500958,0.001165717,0.002549712],"category_scores_gemma":[0.001814687,0.0004295494,0.000686593,0.000401429,0.001030011,0.0007632414,0.000780482,0.002198098,0.0003372139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001168377,"about_ca_system_score_gemma":0.001692662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009158794,"about_ca_topic_score_gemma":0.006557863,"domain_scores_codex":[0.9994513,0.0001691268,0.00003008367,0.0001272494,0.0001623826,0.00005981077],"domain_scores_gemma":[0.9993895,0.0003130659,0.00006114058,0.00003745166,0.0001547991,0.00004400738],"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":[0.00003472679,0.00002290324,0.0002247393,0.0000887922,0.00003231914,0.0000758811,0.00003584499,0.9522182,0.0008950193,0.0299839,0.0008210444,0.01556664],"study_design_scores_gemma":[0.000005521719,0.000009964481,0.00002088582,0.000003075352,0.00000330579,0.000004540163,0.000001306899,0.9966523,0.0001032264,0.002845873,0.0003475731,0.000002501803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003050761,0.0006668943,0.9931113,0.0002138575,0.00007956573,0.0000269366,0.00002815119,0.0002326914,0.002589836],"genre_scores_gemma":[0.8218803,0.0010932,0.1685811,0.0002326764,0.0001530979,0.0003604635,0.0001272742,0.00009901899,0.007472818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009158794,"threshold_uncertainty_score":0.01821095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01559883102852876,"score_gpt":0.2672656284476811,"score_spread":0.2516667974191523,"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."}}