{"id":"W4200400844","doi":"10.32920/17313137","title":"Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Obstacle; Train; Obstacle avoidance; Perception; Trajectory; Action (physics); Object (grammar); Robot; Mobile robot","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"],"consensus_categories":[],"category_scores_codex":[0.0005838972,0.000516004,0.0007624847,0.0001681224,0.0001976398,0.000597883,0.002242521,0.0003996736,0.0002123029],"category_scores_gemma":[0.0003143564,0.0005261801,0.0003625216,0.000323342,0.00009743361,0.0005838095,0.006842223,0.001409012,0.00002936753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002691764,"about_ca_system_score_gemma":0.0005437768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003119078,"about_ca_topic_score_gemma":0.00001642878,"domain_scores_codex":[0.9962412,0.0001817813,0.00119916,0.0009925119,0.0007414431,0.000643863],"domain_scores_gemma":[0.9964114,0.0002433877,0.00105069,0.001791805,0.000382912,0.0001198023],"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":[0.000002395114,0.00002117772,0.000516321,0.0002191803,0.0001439643,0.00001197917,0.002630663,0.9832607,0.001299661,0.007019046,0.00003901414,0.004835933],"study_design_scores_gemma":[0.0002858595,0.0001405451,0.0003716667,0.0002887697,0.00003511157,0.000006564452,0.0002977964,0.9890514,0.007382421,0.000227966,0.001371259,0.0005406238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003690122,0.0002198458,0.9659929,0.0002545743,0.001053502,0.000434864,1.17936e-7,0.0004238772,0.02793017],"genre_scores_gemma":[0.7217826,0.0001718138,0.2727958,0.0001663753,0.00008190915,0.0000307878,0.00003574748,0.00003683157,0.00489817],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7180924,"threshold_uncertainty_score":0.999719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0186631170123467,"score_gpt":0.2561486766434662,"score_spread":0.2374855596311195,"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."}}