{"id":"W2162135116","doi":"10.1109/pads.2010.5471661","title":"A Multi-State Q-Learning Approach for the Dynamic Load Balancing of Time Warp","year":2010,"lang":"en","type":"article","venue":"","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Load balancing (electrical power); Parallel computing; Q-learning; State (computer science); Algorithm design; Distributed computing; Algorithm; Reinforcement learning; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.001844411,0.00006341052,0.0001184806,0.00005466603,0.0001771812,0.00006735756,0.0004607073,0.00004048112,0.0002877637],"category_scores_gemma":[0.0009726657,0.00003438185,0.00008801198,0.00030286,0.00006471988,0.00007533908,0.00006415651,0.0001330919,0.00005760712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009104221,"about_ca_system_score_gemma":0.00003604929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004195204,"about_ca_topic_score_gemma":0.00002588111,"domain_scores_codex":[0.9989455,0.00002402738,0.0003286447,0.0002152754,0.0003705325,0.0001160266],"domain_scores_gemma":[0.9977351,0.001336106,0.0001578358,0.0004085777,0.000330267,0.00003204507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005253849,0.0003173554,0.008139751,0.00001497684,0.00004451455,1.785781e-7,0.002229069,0.0711501,0.4272181,0.006733794,0.007106951,0.4769927],"study_design_scores_gemma":[0.0001512016,0.000012257,0.002407552,9.38456e-7,0.000003982034,8.638925e-7,0.0001502215,0.9806097,0.002095156,0.002199035,0.01231705,0.00005203484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05303703,0.000009706773,0.9428103,0.0002687869,0.00002784656,0.0004313334,0.000007330059,0.00007912557,0.003328536],"genre_scores_gemma":[0.8236424,0.000001862889,0.1610744,0.00005188035,0.00001075599,0.00006109662,0.000002916274,0.000006705037,0.01514793],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9094596,"threshold_uncertainty_score":0.315081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05860159172579892,"score_gpt":0.3916949012031057,"score_spread":0.3330933094773068,"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."}}