{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001339709,0.0001418249,0.0002416947,0.00007767758,0.00003028377,0.00006111651,0.00006679261,0.00004940822,0.0002077451],"category_scores_gemma":[0.00002626644,0.0001118157,0.0001784137,0.0001214413,0.000008273962,0.00007350705,0.000003352052,0.00005698081,0.00003885855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006175302,"about_ca_system_score_gemma":0.0000110197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000243534,"about_ca_topic_score_gemma":0.000003276396,"domain_scores_codex":[0.999285,0.00001115075,0.0002199457,0.0001681672,0.0001006633,0.0002150729],"domain_scores_gemma":[0.9993917,0.0004008014,0.0000100087,0.0001120057,0.00003522115,0.00005022343],"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":[0.000005747303,0.000005072851,2.024454e-7,0.00006840388,0.000473715,9.581084e-7,0.00003577983,0.9832305,0.000795607,0.009211828,0.0006425917,0.005529602],"study_design_scores_gemma":[0.0004086492,0.00002259199,9.472298e-7,0.000007860957,0.0003298318,0.000002301052,0.0000138097,0.9809808,0.000218952,0.0001013301,0.01778475,0.0001281839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002990003,0.002845143,0.9935102,0.0001008718,0.0004415936,0.0006318747,0.00007884361,0.00123364,0.0008588249],"genre_scores_gemma":[0.9856209,0.000004407892,0.01338886,0.00003698423,0.0001566628,0.0003859438,0.00001469339,0.0000503442,0.0003411973],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853219,"threshold_uncertainty_score":0.455971,"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."}}