{"id":"W4308140687","doi":"10.1142/s0219843622500219","title":"Reinforcement Learning for Bipedal Gait with MAX-E2 Humanoid Robot","year":2022,"lang":"en","type":"article","venue":"International Journal of Humanoid Robotics","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Mitacs","keywords":"Humanoid robot; Reinforcement learning; Computer science; Gait; Robot; Parametric statistics; Q-learning; Artificial intelligence; Simulation","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003098193,0.0001843871,0.0002585873,0.0003068898,0.0002183916,0.00009771763,0.0005622992,0.00003530911,0.0004935779],"category_scores_gemma":[0.00002983364,0.000170589,0.0001817826,0.00008634748,0.00003270043,0.0001921584,0.00007953719,0.0004904025,0.000008798758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003513118,"about_ca_system_score_gemma":0.00009363866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002830898,"about_ca_topic_score_gemma":0.000002691534,"domain_scores_codex":[0.9982202,0.00003854126,0.0006020125,0.0001194938,0.0007732625,0.0002464901],"domain_scores_gemma":[0.9990357,0.00007133665,0.0002916499,0.0001160228,0.0003925334,0.00009275314],"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":[0.0001361011,0.00006312924,0.0002143341,0.00001476614,0.0003745374,0.0000581978,0.0002782961,0.9914802,0.00123499,0.002616948,0.002392966,0.001135481],"study_design_scores_gemma":[0.008601631,0.002175053,0.0009421534,0.0001137656,0.0002266637,0.0009623855,0.001065656,0.9246348,0.001286802,0.001017207,0.05824121,0.000732696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0127237,0.000374334,0.9790047,0.001190084,0.003290136,0.0003387584,0.000006093363,0.0001184585,0.002953777],"genre_scores_gemma":[0.9899209,0.00004474869,0.00658332,0.0002223541,0.0006277784,0.00002592492,0.00002568302,0.00005314051,0.002496189],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771972,"threshold_uncertainty_score":0.6956416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01085213223107623,"score_gpt":0.2290392555915959,"score_spread":0.2181871233605197,"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."}}