{"id":"W4405170942","doi":"10.1016/j.comcom.2024.108024","title":"Enhancing fog load balancing through lifelong transfer learning of reinforcement learning agents","year":2024,"lang":"en","type":"article","venue":"Computer Communications","topic":"Smart Parking Systems Research","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Reinforcement learning; Transfer of learning; Lifelong learning; Transfer (computing); Artificial intelligence; Human–computer interaction; Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000577718,0.0001759784,0.0002519043,0.000154569,0.0002468636,0.0001320541,0.0007473819,0.00008094673,0.00004734889],"category_scores_gemma":[0.00004008192,0.000193632,0.0001194196,0.0004754181,0.00006521343,0.0002583567,0.0003110602,0.0008022315,0.0001218274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002502417,"about_ca_system_score_gemma":0.00007945728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009686473,"about_ca_topic_score_gemma":0.00003174352,"domain_scores_codex":[0.9983938,0.0001926316,0.0005251982,0.0001965403,0.0003636121,0.0003281957],"domain_scores_gemma":[0.9984385,0.0004769747,0.00002392526,0.0008845101,0.0001139007,0.00006212453],"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":[0.000003372429,0.00002755355,0.001638527,0.001021836,0.0003656046,0.000008870921,0.01909649,0.9446818,0.01306245,0.002889454,0.001725306,0.01547868],"study_design_scores_gemma":[0.0001507301,0.00004063227,0.0005528125,0.0009722735,0.00001968526,0.0000105721,0.000157329,0.8921146,0.003116383,0.00002267609,0.1026554,0.0001868392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04964033,0.005133081,0.9322188,0.0001741206,0.0006266395,0.0003226659,0.000001391345,0.000970706,0.01091224],"genre_scores_gemma":[0.9909508,0.0006831974,0.007660233,0.00001688737,0.0001594148,0.00005381764,0.00003056164,0.00006110578,0.000383989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9413105,"threshold_uncertainty_score":0.7896082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03827774775568,"score_gpt":0.2996407721707222,"score_spread":0.2613630244150422,"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."}}