{"id":"W4207045767","doi":"10.1109/tcsii.2022.3145373","title":"Parallel Deep Reinforcement Learning Method for Gait Control of Biped Robot","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Gait; Robot; Biped robot; Artificial intelligence; Process (computing); Markov decision process; Control theory (sociology); Control (management); Simulation; Markov process; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005351026,0.000296064,0.000603894,0.0002446097,0.0005936698,0.00004218156,0.0003038213,0.0001004077,0.0002295488],"category_scores_gemma":[0.000009187985,0.0003333249,0.0003127661,0.0002366305,0.00002522606,0.0001347472,0.000002706211,0.0004306588,0.000008455888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002044211,"about_ca_system_score_gemma":0.00004446885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000140528,"about_ca_topic_score_gemma":0.000006501814,"domain_scores_codex":[0.9977003,0.0002619233,0.0007746535,0.0003369251,0.0004813421,0.0004448051],"domain_scores_gemma":[0.9988566,0.0003191773,0.0001726439,0.0004063289,0.0001078355,0.0001373891],"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":[0.00005466772,0.00009448074,0.000001754652,0.0001895425,0.0003069644,0.000002343598,0.0009708485,0.9623511,0.02771445,0.0004589506,0.0001608664,0.007694008],"study_design_scores_gemma":[0.004156782,0.0003833169,0.000007045383,0.00006085386,0.0001480205,0.00002827474,0.0006351151,0.9772558,0.003256401,0.00001359133,0.01369987,0.0003548781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001981321,0.000375196,0.9949054,0.00005737684,0.001656733,0.001594094,0.00004831712,0.0003920374,0.0007727091],"genre_scores_gemma":[0.9943805,0.00001991217,0.0008845002,0.00008124736,0.00008642359,0.002457117,0.00001318072,0.00008485134,0.00199221],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9941824,"threshold_uncertainty_score":0.9999119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01511816134001685,"score_gpt":0.2322888629535888,"score_spread":0.217170701613572,"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."}}