{"id":"W3213426571","doi":"10.1109/tmech.2021.3120628","title":"A Behavior-Based Reinforcement Learning Approach to Control Walking Bipedal Robots Under Unknown Disturbances","year":2021,"lang":"en","type":"article","venue":"IEEE/ASME Transactions on Mechatronics","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Inverted pendulum; Reinforcement learning; Control theory (sociology); Computer science; Robot; Robustness (evolution); Bipedalism; Controller (irrigation); Disturbance (geology); Robot locomotion; Control engineering; Robot control; Artificial intelligence; Control (management); Mobile robot; Engineering; Nonlinear system","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":[0.0001905718,0.0003551131,0.0003786855,0.0001840397,0.0002991225,0.0001267035,0.0002003366,0.0001682068,0.0002099956],"category_scores_gemma":[0.000006930119,0.0003734704,0.0002659137,0.0004296054,0.00002537559,0.0001470806,0.000002444558,0.0006540851,0.00009989466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003903202,"about_ca_system_score_gemma":0.0001248625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001217042,"about_ca_topic_score_gemma":0.00003944515,"domain_scores_codex":[0.9980316,0.000100396,0.0004287318,0.0004223846,0.000436414,0.0005805167],"domain_scores_gemma":[0.9991231,0.00007946631,0.00004990882,0.0004102992,0.0001018756,0.0002353409],"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":[0.00003575776,0.0001937318,0.000005262647,0.00003790186,0.0001094478,0.000006078325,0.0001236107,0.9842322,0.003174199,0.001683475,0.00003584623,0.01036243],"study_design_scores_gemma":[0.0027813,0.0002194713,0.00005765715,0.00006598133,0.000243742,0.00001310407,0.000324513,0.9840176,0.008558596,0.00005270187,0.003092651,0.0005727098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004698731,0.000236008,0.9912266,0.0003010834,0.0009228223,0.0005312678,0.000009868292,0.000564596,0.001509068],"genre_scores_gemma":[0.9927788,0.00004431009,0.00523357,0.0003676273,0.00008000181,0.0004028846,0.00002557536,0.00007729026,0.0009899354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9880801,"threshold_uncertainty_score":0.9998717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01223155664040403,"score_gpt":0.2186668019377259,"score_spread":0.2064352452973219,"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."}}