{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003838545,0.0006645198,0.0007283749,0.0003273552,0.0003341773,0.0004510266,0.0008679074,0.0005298866,0.002677203],"category_scores_gemma":[0.0006388537,0.0003382128,0.0003888514,0.0002617557,0.0003857259,0.0004863639,0.0007178002,0.0008235388,0.0003713987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005993827,"about_ca_system_score_gemma":0.0009302119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005883213,"about_ca_topic_score_gemma":0.004378857,"domain_scores_codex":[0.9998276,0.00002716096,0.00001092694,0.00004580766,0.0000573316,0.00003111867],"domain_scores_gemma":[0.9998198,0.0000437905,0.00002609188,0.00001888211,0.00007091669,0.00002055103],"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":[0.00006541039,0.00003906418,0.0004996049,0.00007459964,0.00004735723,0.0000946837,0.00004193562,0.8783066,0.004359082,0.008606291,0.001814398,0.106051],"study_design_scores_gemma":[0.000004618457,0.00001367314,0.00002459462,0.000001849732,0.000002823489,0.000007837477,0.000001319981,0.9985726,0.0002323392,0.0008710862,0.0002658335,0.000001542528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008237644,0.0003015277,0.9879745,0.0001217814,0.00007663638,0.00002934756,0.00002245325,0.0004637713,0.002772287],"genre_scores_gemma":[0.8419459,0.0003228977,0.1501603,0.0002134697,0.00006345336,0.0001944626,0.0001124917,0.00009377145,0.006893274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005883213,"threshold_uncertainty_score":0.01169795,"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."}}