{"id":"W4310903337","doi":"10.18280/jesa.550514","title":"Simulation of Reinforcement Learning Algorithm for Motion Control of an Autonomous Humanoid","year":2022,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Markov decision process; Q-learning; Computer science; Humanoid robot; Artificial intelligence; Task (project management); Robot; Robotics; Autonomy; Controller (irrigation); Action (physics); Process (computing); Action selection; Markov chain; Machine learning; Human–computer interaction; Markov process; Engineering; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00160033,0.0001814933,0.0003910479,0.0003495886,0.0006608465,0.0001371328,0.00079533,0.00004193083,0.00007109669],"category_scores_gemma":[0.0002519736,0.0001851592,0.0001832274,0.0003309764,0.00006001078,0.0007784227,0.0002068464,0.0003338056,0.000002716436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003027999,"about_ca_system_score_gemma":0.0001590938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001066775,"about_ca_topic_score_gemma":2.093848e-7,"domain_scores_codex":[0.997073,0.0005031835,0.001085092,0.0002297796,0.0007876555,0.000321321],"domain_scores_gemma":[0.9971473,0.0003376604,0.001638336,0.0003513008,0.0004233404,0.0001021118],"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":[0.0000108352,0.00003871542,0.00009273177,0.00005552805,0.00005396579,0.000005468429,0.000861203,0.7641288,0.0005176154,0.001066215,0.00001277927,0.2331561],"study_design_scores_gemma":[0.001244189,0.001963789,0.004802906,0.00004644224,0.00003911878,0.00007718577,0.0001246799,0.9901827,0.0003241464,0.0005461808,0.0004819755,0.0001666745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009537329,0.00009003547,0.9891223,0.00002607482,0.000405074,0.0004487409,0.000004667937,0.0001342555,0.0002314696],"genre_scores_gemma":[0.9090432,0.000005072956,0.09029695,0.00003187817,0.00007311274,0.00002045242,0.00001168782,0.0000264565,0.0004911734],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8995059,"threshold_uncertainty_score":0.7550573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02035538598490284,"score_gpt":0.2687916802652187,"score_spread":0.2484362942803158,"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."}}