{"id":"W4307526217","doi":"10.32920/21408567","title":"Policy-Gradient and Actor-Critic Based State Representation Learning for Safe Driving of Autonomous Vehicles","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Representation (politics); Computer science; Artificial intelligence; Reinforcement learning; Perception; Scheme (mathematics); Object (grammar); Function (biology); Deep learning; 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":[0.0006218325,0.0001960871,0.0003150084,0.00033641,0.0002392761,0.0001849828,0.0005513253,0.00006614548,0.00002860902],"category_scores_gemma":[0.0004196348,0.0002014731,0.0001224954,0.0001864428,0.00004211208,0.0001094308,0.001180683,0.0004255009,0.000001007158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009702771,"about_ca_system_score_gemma":0.0002830029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001493223,"about_ca_topic_score_gemma":0.00002990002,"domain_scores_codex":[0.998184,0.0002579798,0.0003656154,0.0006355824,0.0002684906,0.0002882801],"domain_scores_gemma":[0.9984995,0.0005331291,0.0002798734,0.0005132829,0.0000806388,0.0000935405],"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":[0.00003534647,0.0001547434,0.03135284,0.0009157046,0.0001055927,0.000009764942,0.006179254,0.6187997,0.001076203,0.0174397,0.0003457261,0.3235855],"study_design_scores_gemma":[0.0003952408,0.0001676442,0.02281684,0.00006646126,0.00001493672,0.000002842625,0.00009814703,0.966862,0.0006704641,0.005819446,0.002822282,0.0002637212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3441025,0.00008541012,0.6499876,0.003025408,0.0003423113,0.0004581544,0.000008065758,0.0003000801,0.001690469],"genre_scores_gemma":[0.9577287,0.00002219226,0.04012042,0.0001200825,0.0000550966,0.00007745079,0.00003650109,0.00002066427,0.001818828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6136262,"threshold_uncertainty_score":0.8215834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01893716255583813,"score_gpt":0.3051433549824593,"score_spread":0.2862061924266212,"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."}}