{"id":"W4393187245","doi":"10.2139/ssrn.4773667","title":"Iorl: Inductive-Offline-Reinforcement-Learning for Traffic Signal Control Warmstarting","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Reinforcement learning; SIGNAL (programming language); Control (management); Computer science; Reinforcement; Traffic signal; Artificial intelligence; Psychology; Social psychology; Real-time computing","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":[0.001754236,0.00139406,0.001175227,0.0004703974,0.0005057224,0.0007986097,0.002298008,0.00154726,0.0102875],"category_scores_gemma":[0.005341001,0.0006198035,0.0007108763,0.0003429013,0.001265427,0.001133312,0.003055402,0.003449646,0.00228936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008590012,"about_ca_system_score_gemma":0.001369391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00381323,"about_ca_topic_score_gemma":0.004108189,"domain_scores_codex":[0.9993159,0.0002035715,0.00002956088,0.0001899688,0.0001521413,0.0001089612],"domain_scores_gemma":[0.9982325,0.001003636,0.00009866722,0.0002768695,0.0002721231,0.0001161602],"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":[0.0001935703,0.0001975055,0.0005019443,0.0001559341,0.00005236693,0.0000914808,0.0001280545,0.7678402,0.003313743,0.01716432,0.005778311,0.2045826],"study_design_scores_gemma":[0.00001551795,0.00002439715,0.00003075154,0.00000573115,0.000002906447,0.00000728155,0.000002748879,0.9943759,0.0007832497,0.004223941,0.0005234383,0.000004101094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00291203,0.0000806984,0.9911857,0.00007812961,0.00006392517,0.00004534011,0.00003432031,0.003753834,0.0018461],"genre_scores_gemma":[0.5216897,0.0001278124,0.4644975,0.0003509095,0.0001458624,0.0005254422,0.0003428546,0.001341222,0.01097871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0102875,"threshold_uncertainty_score":0.03441507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007815133686983063,"score_gpt":0.2297182497005814,"score_spread":0.2219031160135984,"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."}}