{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001257755,0.0007571916,0.0007842148,0.0003733851,0.0003169756,0.0005829859,0.0009426424,0.0007491797,0.001739981],"category_scores_gemma":[0.004328225,0.0004121295,0.0003895936,0.0002861963,0.0009534749,0.0008381802,0.0007582512,0.001175435,0.0001854972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008742844,"about_ca_system_score_gemma":0.001159221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003986011,"about_ca_topic_score_gemma":0.002768383,"domain_scores_codex":[0.9995989,0.0001627479,0.0000212348,0.00006356963,0.0001037692,0.00004974832],"domain_scores_gemma":[0.9978387,0.001603523,0.0001866973,0.0001220585,0.0001779075,0.00007111508],"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":[0.0000187983,0.00001310434,0.0001115484,0.000007945337,0.000005254257,0.000009857643,0.000009427477,0.9943743,0.0004157875,0.001408965,0.00003728334,0.003587642],"study_design_scores_gemma":[0.000005633325,0.000008393981,0.000008281966,9.393997e-7,0.00000122773,0.000001630384,0.000001334166,0.9990205,0.0002536377,0.0006523613,0.00004523619,8.882216e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04532871,0.0001057522,0.9518477,0.0001289125,0.00001754858,0.00007328477,0.00001405433,0.0003553265,0.002128778],"genre_scores_gemma":[0.8821888,0.0001017407,0.1161661,0.00004621573,0.0000120676,0.0002040081,0.00002700935,0.00005536232,0.001198828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003986011,"threshold_uncertainty_score":0.00792563,"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."}}