{"id":"W4324006961","doi":"10.2139/ssrn.4385976","title":"Iorl: Inductive-Offline-Reinforcement-Learning for Traffic Signal Control Warmstarting","year":2023,"lang":"en","type":"article","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; Computer science; Control (management); SIGNAL (programming language); Traffic signal; Reinforcement; Artificial intelligence; Psychology; Real-time computing; Social psychology","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":[0.001722908,0.001266246,0.001103453,0.0004857421,0.0004968051,0.0007262636,0.002250075,0.001404318,0.009782139],"category_scores_gemma":[0.004706315,0.0005636023,0.0006662875,0.000314662,0.001101424,0.001013786,0.002734569,0.003102479,0.002077805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008116504,"about_ca_system_score_gemma":0.001373608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005014751,"about_ca_topic_score_gemma":0.005392574,"domain_scores_codex":[0.9993267,0.0001918042,0.0000301888,0.0001786094,0.0001545343,0.0001182525],"domain_scores_gemma":[0.9983807,0.0008795162,0.00009634314,0.000236171,0.0002989972,0.000108359],"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":[0.0002058723,0.0002190271,0.0005362653,0.0001374097,0.00005038747,0.00009595782,0.0001247257,0.7496538,0.003403525,0.01164183,0.005154823,0.2287764],"study_design_scores_gemma":[0.00001422599,0.00002790384,0.0000336402,0.000005282908,0.000002934417,0.000007698361,0.000002936702,0.9961894,0.0008102329,0.002386908,0.0005146719,0.000004178749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003503252,0.0000838434,0.9896255,0.00006997325,0.00006662939,0.00005103705,0.00003205651,0.004523066,0.002044668],"genre_scores_gemma":[0.5516191,0.000109357,0.4359224,0.0003077291,0.0001179809,0.0004515558,0.0002936302,0.001072341,0.01010591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009782139,"threshold_uncertainty_score":0.0327245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008049761483226522,"score_gpt":0.2234237357549814,"score_spread":0.2153739742717549,"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."}}