{"id":"W4385473744","doi":"10.48550/arxiv.2307.16062","title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Generalizability theory; Robot; Artificial intelligence; Heuristic; Motion planning; Motion (physics); Kinematics; Simulation; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075246,0.0007048932,0.0004903584,0.0002851067,0.000261876,0.0003748405,0.001337492,0.0006584172,0.001753597],"category_scores_gemma":[0.003579765,0.0003573038,0.0004214405,0.0002732987,0.001069476,0.0009667943,0.0008797157,0.001662115,0.0004338961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005603554,"about_ca_system_score_gemma":0.001135763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003762633,"about_ca_topic_score_gemma":0.005088873,"domain_scores_codex":[0.9995375,0.0001868484,0.00002449957,0.0001357744,0.00008000973,0.00003540477],"domain_scores_gemma":[0.998539,0.0007079616,0.0001802886,0.0003612399,0.000127029,0.00008448908],"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":[0.0002803203,0.0003945848,0.003731001,0.0002547401,0.00006670921,0.0001415373,0.0001749557,0.6716284,0.02601065,0.01137656,0.002336971,0.2836036],"study_design_scores_gemma":[0.00002422911,0.00008249065,0.0003333914,0.000006287782,0.000006751526,0.00002095597,0.000006709298,0.9920077,0.003672704,0.002907474,0.00092417,0.000007070831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05324686,0.0002395747,0.9416606,0.0002382368,0.00004395286,0.0001213635,0.0000958162,0.002574718,0.001778787],"genre_scores_gemma":[0.6958013,0.0001366599,0.3016371,0.0001267485,0.00001778497,0.0001982215,0.0002231461,0.0001289499,0.001730202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003762633,"threshold_uncertainty_score":0.007481456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.212502004908271,"score_gpt":0.2636145749693694,"score_spread":0.05111257006109834,"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."}}