{"id":"W3093511015","doi":"10.3390/s20215991","title":"Policy-Gradient and Actor-Critic Based State Representation Learning for Safe Driving of Autonomous Vehicles","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Computer science; Representation (politics); Artificial intelligence; Reinforcement learning; Perception; Scheme (mathematics); Object (grammar); Function (biology); Deep learning; Machine learning; Simulation; Mathematics; Psychology; Law","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":[0.0001509514,0.0001056709,0.0001640605,0.0001016107,0.000104194,0.00008378374,0.0002096169,0.00003043937,0.000002127578],"category_scores_gemma":[0.0006978499,0.0001111698,0.00005201232,0.0002480782,0.00005394307,0.0001557445,0.00009628321,0.0001139614,0.000003808147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003404307,"about_ca_system_score_gemma":0.00006947983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003591029,"about_ca_topic_score_gemma":0.000001343438,"domain_scores_codex":[0.9989592,0.00008324537,0.0002575035,0.0002776532,0.0001900342,0.0002323704],"domain_scores_gemma":[0.9991188,0.0003557546,0.000151853,0.000185479,0.0000786345,0.0001094611],"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":[0.000009572901,0.000005728949,0.0052505,0.00006641902,0.00001327916,0.00000273698,0.00264626,0.9796364,0.005182632,0.001544797,0.00002523103,0.005616461],"study_design_scores_gemma":[0.0003617695,0.0002056605,0.006242771,0.00002507352,0.000007051584,0.00000131165,0.0001284568,0.9820435,0.01015954,0.0001379827,0.0005740795,0.0001128217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4318157,0.000009886445,0.565416,0.002239115,0.00005606497,0.0001894794,8.750924e-7,0.00009946193,0.0001734462],"genre_scores_gemma":[0.9745815,0.000008388082,0.0249665,0.0002078198,0.00004226417,0.000004331711,0.00000385272,0.00001310987,0.0001721933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5427659,"threshold_uncertainty_score":0.4533375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02501525026013139,"score_gpt":0.2744572081329379,"score_spread":0.2494419578728065,"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."}}