{"id":"W4402474809","doi":"10.1109/ccece59415.2024.10667211","title":"Sample-Efficient Meta-RL for Traffic Signal Control","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; McGill University","funders":"","keywords":"Sample (material); Computer science; SIGNAL (programming language); Traffic signal; 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":[0.001526295,0.001697955,0.001640384,0.0006891054,0.0004371493,0.00135067,0.001773646,0.001384275,0.002664575],"category_scores_gemma":[0.004923188,0.0008110065,0.001212504,0.0005895167,0.001122802,0.001329735,0.001656325,0.002385176,0.0004569233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214893,"about_ca_system_score_gemma":0.001813196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006745034,"about_ca_topic_score_gemma":0.007252447,"domain_scores_codex":[0.9994327,0.0002363976,0.00002779557,0.0001123509,0.0001015944,0.00008909744],"domain_scores_gemma":[0.9981112,0.001294111,0.0001518991,0.0001654012,0.0001764553,0.0001009023],"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":[0.00004212651,0.00002695394,0.0003127689,0.0000438091,0.00003771082,0.00002215839,0.00001566615,0.9860756,0.0002512337,0.002776386,0.0004603916,0.009935183],"study_design_scores_gemma":[0.000007284019,0.00001297054,0.00002546032,0.000004663173,0.000005148953,0.000002888157,0.000002790029,0.997488,0.00007792306,0.002243929,0.0001270593,0.000001919085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02845681,0.00121709,0.9645352,0.0005691506,0.00009321672,0.0000738438,0.0002035885,0.001395902,0.00345518],"genre_scores_gemma":[0.8907116,0.0003929137,0.1050986,0.0003421408,0.00006926944,0.0002875671,0.0004652523,0.0002418516,0.002390798],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006745034,"threshold_uncertainty_score":0.01341158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01576716413636493,"score_gpt":0.2309057990094168,"score_spread":0.2151386348730518,"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."}}