{"id":"W4400146922","doi":"10.1016/j.knosys.2024.112190","title":"DiffSkill: Improving Reinforcement Learning through diffusion-based skill denoiser for robotic manipulation","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"China Scholarship Council; Science and Technology Commission of Shanghai Municipality","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Materials science; Composite material","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001214973,0.0008483168,0.001087272,0.0005325167,0.0004329991,0.0005586437,0.001895668,0.001337083,0.0038456],"category_scores_gemma":[0.003502348,0.000400863,0.0004230735,0.0002965785,0.001003196,0.001078583,0.001991411,0.001969578,0.0006040239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006998783,"about_ca_system_score_gemma":0.00106474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005614593,"about_ca_topic_score_gemma":0.007396366,"domain_scores_codex":[0.9995993,0.00006916912,0.00002202539,0.0001004322,0.0001518563,0.00005731331],"domain_scores_gemma":[0.9988638,0.0005812473,0.0000956019,0.0001274086,0.0002369516,0.00009499209],"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":[0.0004158015,0.0004156288,0.0007319421,0.0001883128,0.00007211825,0.0001052117,0.000100917,0.6663162,0.01843665,0.009675002,0.003183808,0.3003585],"study_design_scores_gemma":[0.0000271553,0.00006307574,0.00006106787,0.000004896785,0.000005515514,0.00001226876,0.000003831325,0.9955665,0.00207685,0.001811469,0.0003615968,0.000005783981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02941159,0.0003700237,0.9651092,0.0002009437,0.0001520329,0.00008901062,0.00003876582,0.001834565,0.002793785],"genre_scores_gemma":[0.7914621,0.0001440162,0.2008868,0.0002698663,0.00004557466,0.0001544019,0.0001006201,0.0002006787,0.006735952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005614593,"threshold_uncertainty_score":0.01286483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0254441504376951,"score_gpt":0.2764469236046732,"score_spread":0.2510027731669781,"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."}}