{"id":"W7124291073","doi":"10.65109/yptr7088","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalization; Reinforcement learning; Focus (optics); Artificial neural network; Contrast (vision); Deep learning; Control (management)","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":[0.001313398,0.0005743781,0.0004540123,0.00104484,0.0009247568,0.003472132,0.0007343452,0.0002761574,0.0006642414],"category_scores_gemma":[0.0006446293,0.0006352959,0.0002682769,0.002265195,0.00007714285,0.001491579,0.0005571561,0.001138138,0.0007224854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008489742,"about_ca_system_score_gemma":0.0004191143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001680264,"about_ca_topic_score_gemma":0.00007092818,"domain_scores_codex":[0.9949588,0.0002438645,0.001384558,0.001297847,0.0008530958,0.001261843],"domain_scores_gemma":[0.9982244,0.0005032772,0.000231842,0.0004482293,0.0002240364,0.0003682066],"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":[0.00002946923,0.0000394348,0.0007568306,0.0002708448,0.00007404706,0.00002290821,0.005888581,0.9324499,0.0006448235,0.02809709,0.0003489477,0.03137711],"study_design_scores_gemma":[0.0004480265,0.001128803,0.0002591935,0.0003779928,0.00005222136,0.00001448085,0.0007312148,0.9087389,0.000409779,0.0000709657,0.08708652,0.0006818885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002458168,0.0002622352,0.9860392,0.001662605,0.002678952,0.00147401,5.40849e-7,0.0005818425,0.004842423],"genre_scores_gemma":[0.9067401,0.0001654973,0.02400345,0.0003267459,0.0004503028,0.0002106101,0.0001012992,0.0000935749,0.06790847],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9620358,"threshold_uncertainty_score":0.9996098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02183426322905901,"score_gpt":0.3108022284253805,"score_spread":0.2889679651963215,"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."}}