{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007068366,0.0007486159,0.0007863347,0.0004062203,0.0003974195,0.0004893044,0.001022241,0.0006806211,0.00143897],"category_scores_gemma":[0.001413691,0.0003219045,0.0005025063,0.0002655653,0.0005523133,0.0005935621,0.0007130229,0.0009888201,0.0002165604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006596549,"about_ca_system_score_gemma":0.001178557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006022731,"about_ca_topic_score_gemma":0.0035719,"domain_scores_codex":[0.9996514,0.00009437198,0.00002087875,0.00009187393,0.0000901344,0.00005143051],"domain_scores_gemma":[0.9994469,0.0002596056,0.00007113024,0.00002848118,0.0001440524,0.00004979126],"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":[0.0000711196,0.00009618857,0.00100844,0.00007179417,0.00004981106,0.0001118274,0.00008068889,0.9075377,0.004100228,0.009563346,0.001046509,0.0762623],"study_design_scores_gemma":[0.000006440651,0.00001589143,0.00003824472,0.00000175845,0.000003597115,0.000007194418,0.000002054786,0.9988829,0.0002055415,0.0006816851,0.0001517842,0.000002744146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01205558,0.0001838581,0.985558,0.0001298802,0.0000529094,0.00004404338,0.00001220839,0.0002839112,0.001679649],"genre_scores_gemma":[0.8901578,0.0001929103,0.1066292,0.0001365828,0.00005374825,0.0001798863,0.00004793009,0.00004838628,0.002553407],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006022731,"threshold_uncertainty_score":0.01197535,"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."}}