{"id":"W4388483498","doi":"10.1109/ase56229.2023.00121","title":"An Intentional Forgetting-Driven Self-Healing Method for Deep Reinforcement Learning Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Forgetting; Reinforcement learning; Convergence (economics); Computer science; Adaptation (eye); Reinforcement; Artificial intelligence; Cognitive psychology; Engineering; Psychology","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":[0.001380085,0.0007548188,0.0007451241,0.0004022723,0.0003798585,0.0005735988,0.001550213,0.0007581536,0.001942336],"category_scores_gemma":[0.002420658,0.0003492674,0.0005263742,0.000216017,0.0006939116,0.0007412296,0.001306367,0.001278333,0.0002823682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007441041,"about_ca_system_score_gemma":0.000943982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00327157,"about_ca_topic_score_gemma":0.003287264,"domain_scores_codex":[0.9995134,0.0001219741,0.00003898064,0.0001082896,0.0001373965,0.00008001544],"domain_scores_gemma":[0.9990562,0.0003714064,0.0001456576,0.000120505,0.0002199466,0.00008626161],"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":[0.0001120833,0.00009461701,0.001361753,0.0001227032,0.00006613274,0.0001048869,0.0001473168,0.8266681,0.007072733,0.00784336,0.001588657,0.1548177],"study_design_scores_gemma":[0.000008782428,0.00002953995,0.00004717047,0.000003593655,0.000004884858,0.00001058305,0.00000369295,0.9980411,0.0005048758,0.001053746,0.0002889993,0.000003084969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02624189,0.0003433716,0.9699469,0.0002062104,0.00006556744,0.00006636362,0.00002342296,0.001272774,0.001833419],"genre_scores_gemma":[0.8782208,0.0001401469,0.1184688,0.0002474907,0.0000487838,0.0001530463,0.00006331343,0.0001172059,0.002540397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00327157,"threshold_uncertainty_score":0.007298708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02687934710323557,"score_gpt":0.3167402699521178,"score_spread":0.2898609228488823,"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."}}