{"id":"W4298946154","doi":"10.1109/jiot.2022.3196639","title":"A Behavior Decision Method Based on Reinforcement Learning for Autonomous Driving","year":2022,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Western University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Markov decision process; Exploit; Function (biology); Collision avoidance; Process (computing); Q-learning; Markov process; Artificial intelligence; Collision; Simulation; Computer security","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":[0.001137916,0.0001539987,0.0002472052,0.0003009476,0.0002177783,0.00002856662,0.0004208462,0.00008886879,0.0003222957],"category_scores_gemma":[0.00007788576,0.0001579651,0.0001977205,0.00009105504,0.00002257445,0.0001256736,0.00006544852,0.001100672,0.000004144411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003606954,"about_ca_system_score_gemma":0.00004063995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007448711,"about_ca_topic_score_gemma":6.876236e-7,"domain_scores_codex":[0.9987701,0.00005131237,0.0005033279,0.000146487,0.0002626504,0.0002660895],"domain_scores_gemma":[0.9992667,0.0002621316,0.0002120557,0.0001513827,0.00004719246,0.00006049836],"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":[0.00009877395,0.00004019292,0.000424963,0.00001257221,0.00004301595,0.00002291352,0.0005542943,0.9247011,0.004141952,0.0001502741,0.0007373565,0.06907262],"study_design_scores_gemma":[0.0007247998,0.0007088881,0.000208393,0.00006913024,0.00004142286,0.0001627246,0.0001084564,0.9701126,0.02091723,0.0003023848,0.006479224,0.0001647406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2529922,0.00003128102,0.7452249,0.00006535111,0.0008144519,0.0001583806,9.509362e-7,0.0001810276,0.0005315081],"genre_scores_gemma":[0.9643315,0.000004207485,0.03507618,0.0001103571,0.00004408456,0.000061917,0.000002389638,0.00003841492,0.0003309658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7113393,"threshold_uncertainty_score":0.6441632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01105087786779846,"score_gpt":0.2621755977297501,"score_spread":0.2511247198619517,"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."}}