{"id":"W4230667489","doi":"10.1109/wsc.2007.4419650","title":"Optimizing time warp simulation with reinforcement learning techniques","year":2007,"lang":"en","type":"article","venue":"2007 Winter Simulation Conference","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Benchmark (surveying); Bellman equation; Dynamic programming; Function (biology); Bounded function; State (computer science); Optimal control; Artificial intelligence; Mathematical optimization; Algorithm; 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":[0.000337165,0.0002194357,0.0001814342,0.0002027019,0.00008248282,0.00008070598,0.0001296309,0.0001292757,0.0004762262],"category_scores_gemma":[0.0000270938,0.0002073147,0.00004169927,0.0001647464,0.00003277919,0.0003823762,0.00002588585,0.0002450018,0.00008324596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075899,"about_ca_system_score_gemma":0.00001386386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004599607,"about_ca_topic_score_gemma":0.000002305044,"domain_scores_codex":[0.9988784,0.00001970969,0.0003516271,0.0002057521,0.0002341032,0.0003104651],"domain_scores_gemma":[0.9993004,0.0001499164,0.00007508157,0.0002001357,0.0001948797,0.00007965464],"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":[0.00003495384,0.000007094196,0.00021477,0.00001798936,0.00001856348,0.00000501043,0.0004648258,0.9750378,0.004405029,0.00007452913,0.00005526495,0.01966416],"study_design_scores_gemma":[0.0001755826,0.0001391937,0.000183584,0.0001280943,0.00001279013,0.000001829675,0.00003791109,0.9577306,0.03488078,0.00004886664,0.006379082,0.0002816844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007293009,0.00002459291,0.963795,0.000008311861,0.00005572368,0.0003110637,7.034507e-7,0.001696051,0.02681555],"genre_scores_gemma":[0.9783402,0.000006898003,0.0205341,0.00005044292,0.0001119001,0.00001033543,0.00002730483,0.00004320319,0.0008756286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9710472,"threshold_uncertainty_score":0.845405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01691587200443344,"score_gpt":0.2577633236223327,"score_spread":0.2408474516178992,"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."}}