{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005679645,0.0004866892,0.0004575592,0.000601518,0.0005457363,0.0003175539,0.0009417218,0.0002516664,0.000003873577],"category_scores_gemma":[0.0001177875,0.0006245208,0.0001864641,0.0004893101,0.00006170582,0.0004376493,0.003092192,0.0006906686,0.00002070067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008824258,"about_ca_system_score_gemma":0.0001260951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002282777,"about_ca_topic_score_gemma":0.000009984131,"domain_scores_codex":[0.9970641,0.0001110326,0.0004496003,0.001435467,0.0002125751,0.0007272183],"domain_scores_gemma":[0.9981001,0.0002047155,0.0004684317,0.0007389038,0.0002381385,0.0002497102],"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":[0.00002786666,0.00001383791,0.002840456,0.0001328024,0.00009481981,0.00006100232,0.001435157,0.9890439,0.00108259,0.004835548,0.000009202362,0.0004228062],"study_design_scores_gemma":[0.0005341985,0.0002457114,0.004816094,0.0003416271,0.0001337032,0.000002453975,0.0004384876,0.99193,0.0001808483,0.0007173356,0.00004694022,0.0006126009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1520495,0.00001352428,0.8455384,0.00004770053,0.000470788,0.001378588,0.000006125638,0.0003799072,0.0001155348],"genre_scores_gemma":[0.9732543,0.00003289824,0.02322102,0.00008413937,0.00003346554,0.00002113893,0.00007043462,0.00005260733,0.00323004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8223174,"threshold_uncertainty_score":0.9996206,"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."}}