{"id":"W2250923797","doi":"10.5555/1999416.1999484","title":"Synergy of the reinforcement learning and agent-based technique for finding optimal solution in a predefined interval","year":2010,"lang":"en","type":"article","venue":"Summer Computer Simulation Conference","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Interval (graph theory); Actuator; Function (biology); Multi-agent system; Wireless; Q-learning; Artificial intelligence; Mathematical optimization; Engineering; Mathematics","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":[0.0002442564,0.00009858941,0.0001111154,0.00009537457,0.0001444352,0.00004716083,0.0003215469,0.00006190763,0.000009104851],"category_scores_gemma":[0.00003144864,0.00008543013,0.00004939354,0.0002165483,0.00005728505,0.0001946256,0.0001969872,0.000165442,5.820066e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002119617,"about_ca_system_score_gemma":0.00008074219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003090618,"about_ca_topic_score_gemma":0.00002206895,"domain_scores_codex":[0.9991418,0.00004365855,0.000287849,0.0002498558,0.0001289737,0.0001478537],"domain_scores_gemma":[0.9992349,0.000196789,0.0001628085,0.000226836,0.0001472614,0.00003142315],"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":[0.0000140047,0.00006302803,0.004062124,0.00003475397,0.000008193614,1.668123e-7,0.0003133806,0.9142272,0.00812236,0.06198382,0.00003075155,0.01114023],"study_design_scores_gemma":[0.0004323405,0.00006611865,0.006530496,0.00004462287,0.00000302268,7.768728e-7,0.000004639097,0.988793,0.002554025,0.0004862452,0.0009907737,0.00009397067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02489796,0.000004936279,0.9739545,0.0003730851,0.0001769565,0.0004908838,0.000001816812,0.00003524556,0.00006460779],"genre_scores_gemma":[0.8519526,6.137799e-7,0.1478228,0.00003021097,0.00002899624,0.00009839212,0.000008585994,0.000004014285,0.0000537942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8270546,"threshold_uncertainty_score":0.348374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03310957087178093,"score_gpt":0.2911689759997367,"score_spread":0.2580594051279558,"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."}}