{"id":"W4388342252","doi":"10.1002/aisy.202300352","title":"A Multiobjective Collaborative Deep Reinforcement Learning Algorithm for Jumping Optimization of Bipedal Robot","year":2023,"lang":"en","type":"article","venue":"Advanced Intelligent Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Markov decision process; Convergence (economics); Robot; Jumping; Artificial intelligence; Q-learning; Nonlinear system; Robotics; Mathematical optimization; Machine learning; 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":[0.0006121793,0.0002627481,0.0004099688,0.0004109449,0.0002643362,0.0001263124,0.0005544971,0.0001001417,0.000004850736],"category_scores_gemma":[0.0003838306,0.0002673229,0.000116789,0.001552146,0.00005284964,0.0006581635,0.0002034993,0.0001776074,0.00004287954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002447985,"about_ca_system_score_gemma":0.0001004275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000245848,"about_ca_topic_score_gemma":0.000001196144,"domain_scores_codex":[0.9975135,0.0001346812,0.0008376179,0.0005103629,0.0005120725,0.0004917468],"domain_scores_gemma":[0.9974212,0.0004899619,0.0007004862,0.0004261867,0.0008680056,0.00009413905],"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":[0.00001270967,0.00001257741,0.00003596405,0.00009142965,0.00008115228,0.000002031251,0.002291591,0.9802876,0.0004682196,0.002697453,0.0000400501,0.01397929],"study_design_scores_gemma":[0.0004941155,0.0005045191,0.000009198601,0.0001868453,0.00001406988,0.000002557438,0.002414959,0.9863538,0.008029197,0.00002527675,0.001694482,0.0002710313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004343218,0.0001857081,0.9957889,0.00002961155,0.00135102,0.001674891,0.000002733238,0.0004097808,0.00051393],"genre_scores_gemma":[0.4048792,0.0005286456,0.5892338,0.00004290983,0.0001882773,0.0007128771,0.0001914915,0.00008412865,0.004138645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4065551,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02051099909052159,"score_gpt":0.2888989493345185,"score_spread":0.268387950243997,"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."}}