{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009859328,0.000536052,0.0005257902,0.0004310541,0.0006179193,0.001273181,0.0009876929,0.0002453278,0.00002086762],"category_scores_gemma":[0.0003107775,0.0004895524,0.00034717,0.0008570941,0.00006504292,0.0007186047,0.0002065192,0.0004569062,0.0003331944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006862985,"about_ca_system_score_gemma":0.0005021169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001442133,"about_ca_topic_score_gemma":0.00001256819,"domain_scores_codex":[0.9961361,0.0002618084,0.00102126,0.001008752,0.0007051964,0.0008668394],"domain_scores_gemma":[0.9969445,0.001190896,0.0003357714,0.0009714749,0.0003706055,0.0001867835],"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":[0.00001274621,0.0000511221,0.0003508603,0.001593354,0.000047785,0.00001200178,0.0009492659,0.9780678,0.001120709,0.01571984,0.0007034482,0.001371059],"study_design_scores_gemma":[0.001024209,0.0003923628,0.00009390045,0.001071099,0.00006795552,0.000005385194,0.00009407559,0.9836732,0.0009835804,0.00006869056,0.01193348,0.0005920228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006852461,0.001257828,0.9873725,0.0002115871,0.005046661,0.00166872,0.00000107725,0.0013495,0.002406936],"genre_scores_gemma":[0.9795758,0.000004979835,0.01062288,0.0001021502,0.0004382044,0.0004024135,0.00009984796,0.0001092321,0.008644469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9788906,"threshold_uncertainty_score":0.9997636,"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."}}