{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003809578,0.0005631249,0.0005573889,0.0003099213,0.0004669495,0.0005308515,0.0006574459,0.0008562428,0.005314917],"category_scores_gemma":[0.001220516,0.0002133629,0.0004715284,0.0001633265,0.0004495665,0.0003353316,0.0005995262,0.0006737451,0.0002923431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005146398,"about_ca_system_score_gemma":0.0006894019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01263946,"about_ca_topic_score_gemma":0.005206613,"domain_scores_codex":[0.9998385,0.0000511455,0.000009742578,0.00002884388,0.0000360813,0.00003556767],"domain_scores_gemma":[0.9995134,0.0002734004,0.0000508658,0.00002184815,0.0001010306,0.00003941727],"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":[0.00005923838,0.00001993937,0.0005478624,0.00003278744,0.00001017869,0.00007721774,0.00003455038,0.9931479,0.0006955193,0.001620619,0.0001890303,0.003565167],"study_design_scores_gemma":[0.000008641387,0.00002027762,0.00005668071,0.000002793173,0.000002030827,0.000004267854,0.000004423158,0.999298,0.0001457025,0.000308204,0.000147484,0.00000153225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2429263,0.000789019,0.7308134,0.0006170293,0.0002146679,0.0002174072,0.0002495352,0.001512457,0.02266024],"genre_scores_gemma":[0.9745072,0.0001124703,0.0220727,0.00003413782,0.000007793992,0.0001574636,0.00009065715,0.0000187236,0.002998863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01263946,"threshold_uncertainty_score":0.02513176,"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."}}