{"id":"W4225836256","doi":"10.1109/tiv.2022.3167616","title":"Deep Reinforcement Learning With NMPC Assistance Nash Switching for Urban Autonomous Driving","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Toyota Motor Corporation","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005436868,0.0003238748,0.0002746838,0.0003182878,0.001850867,0.0003027272,0.0009999396,0.00005787628,0.0001230782],"category_scores_gemma":[0.00001370039,0.0003283504,0.000191461,0.0005030116,0.00004712548,0.0004434891,0.0000234056,0.0008512852,0.00002651322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005709465,"about_ca_system_score_gemma":0.0001329588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002436892,"about_ca_topic_score_gemma":0.0000210008,"domain_scores_codex":[0.9973224,0.0001356081,0.0005401929,0.0006405758,0.0007521124,0.0006091027],"domain_scores_gemma":[0.9984466,0.0003968414,0.000287117,0.0006112899,0.0001136756,0.0001445068],"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":[0.00007841087,0.00007715464,0.0001622827,0.0000261775,0.00009716175,0.000007515108,0.002018852,0.9757032,0.0005375114,0.002101534,0.00005851214,0.01913168],"study_design_scores_gemma":[0.0004209962,0.001214844,0.00004540035,0.00005469295,0.00003603141,0.00002125147,0.0005866268,0.9750465,0.01263048,0.00007019414,0.009448082,0.0004248938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004438317,0.00004205905,0.9928288,0.0003092021,0.000770069,0.0006359608,9.64374e-7,0.0004949823,0.0004796234],"genre_scores_gemma":[0.9719436,0.00002381126,0.02393445,0.0002696237,0.0000469778,0.0004398812,0.000004498104,0.00005226393,0.003284951],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9688944,"threshold_uncertainty_score":0.9999169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698484467247028,"score_gpt":0.2404053362757641,"score_spread":0.2234204916032938,"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."}}