{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008212305,0.0006071951,0.0005727789,0.000246226,0.000308135,0.0004447003,0.0009180357,0.0006428926,0.001414799],"category_scores_gemma":[0.002449722,0.000302451,0.0003107758,0.0001977154,0.0006018135,0.0004498124,0.0007526273,0.001119291,0.0001885693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008030912,"about_ca_system_score_gemma":0.001272962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262605,"about_ca_topic_score_gemma":0.008239623,"domain_scores_codex":[0.9997471,0.00007266532,0.00001123646,0.00005244765,0.0000600423,0.00005645828],"domain_scores_gemma":[0.9991682,0.000479353,0.0000812142,0.00006094234,0.0001495236,0.00006081513],"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":[0.00009187299,0.00006840259,0.0007548784,0.00002898584,0.00001628789,0.00003480773,0.00003536929,0.9637423,0.001140801,0.001919724,0.0006169388,0.03154952],"study_design_scores_gemma":[0.000004619105,0.00001350322,0.00004214277,8.222474e-7,0.000001162761,0.000001617659,0.000001565724,0.999352,0.0001934622,0.0003175519,0.00007046099,0.000001109409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1507259,0.0003724325,0.8408083,0.0004751746,0.0001022224,0.00009151909,0.00005416027,0.002050449,0.005319925],"genre_scores_gemma":[0.970459,0.00004127126,0.02784011,0.00009895173,0.0000117307,0.00005370229,0.0000400112,0.00003385266,0.001421318],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01262605,"threshold_uncertainty_score":0.02510512,"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."}}