{"id":"W4400727628","doi":"10.1109/rose62198.2024.10590850","title":"A Model-Free Solution for Stackelberg Games Using Reinforcement Learning and Projection Approaches","year":2024,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Stackelberg competition; Reinforcement learning; Computer science; Projection (relational algebra); Mathematical optimization; Artificial intelligence; Mathematical economics; Mathematics; Algorithm","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":[0.0009431909,0.001171944,0.0009797637,0.0003568645,0.0005706708,0.0008603919,0.001103454,0.001190596,0.00219898],"category_scores_gemma":[0.001895783,0.0005705707,0.0007825083,0.0002745329,0.001219303,0.0008182061,0.001604515,0.001862367,0.0003557637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006764976,"about_ca_system_score_gemma":0.002297432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006412483,"about_ca_topic_score_gemma":0.005031497,"domain_scores_codex":[0.9996946,0.0001156461,0.00001090497,0.00004923783,0.00009192391,0.00003770712],"domain_scores_gemma":[0.9994217,0.0003444997,0.00006347035,0.00002648107,0.00009522805,0.00004868469],"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":[0.00001916629,0.00002583104,0.0001361741,0.00004203793,0.00002231841,0.00004511518,0.00005090516,0.9673205,0.0009022851,0.01934526,0.0003635058,0.01172695],"study_design_scores_gemma":[0.000004823435,0.00001622516,0.00001744379,0.00000361715,0.000002282266,0.00000568552,0.000004248677,0.9954321,0.0001304772,0.004183306,0.0001966307,0.000003195395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004258394,0.00005556472,0.9934282,0.00007807588,0.000017062,0.0000277493,0.000009593615,0.00007284854,0.00205254],"genre_scores_gemma":[0.6671244,0.0002493673,0.3249925,0.0001132799,0.00004702143,0.0004273345,0.00007240944,0.00008719846,0.0068865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006412483,"threshold_uncertainty_score":0.01275033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04564035894130787,"score_gpt":0.2329356953928847,"score_spread":0.1872953364515769,"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."}}