{"id":"W4307442681","doi":"10.32920/21408567.v1","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); State (computer science); Deep learning; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008327069,0.0006512003,0.000689467,0.0002935785,0.0002490195,0.0006767284,0.0008941801,0.0008567178,0.00125232],"category_scores_gemma":[0.002037239,0.0005034779,0.0004040292,0.0002419875,0.0007757066,0.0008158339,0.0008287228,0.001310036,0.0002714834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009125777,"about_ca_system_score_gemma":0.001292974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007650658,"about_ca_topic_score_gemma":0.005161775,"domain_scores_codex":[0.9996991,0.0000917825,0.00001185774,0.00008291534,0.000062099,0.00005230313],"domain_scores_gemma":[0.9994323,0.0002781662,0.00007286259,0.00004534646,0.0001212271,0.00004998092],"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":[0.00003336271,0.0000225348,0.0003077863,0.00001878669,0.00001593375,0.00003262706,0.00003152026,0.9745176,0.001174154,0.004670258,0.0004557136,0.01871967],"study_design_scores_gemma":[0.000001207453,0.000005507824,0.00002050062,8.00295e-7,7.205277e-7,0.000001668128,0.000001107116,0.9989743,0.0001165443,0.0008146188,0.00006187876,0.000001059868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02599314,0.0002079843,0.9711359,0.000299742,0.00004799838,0.00002297453,0.00003258678,0.0005279296,0.001731838],"genre_scores_gemma":[0.9293201,0.0001124572,0.06597053,0.0001274852,0.00003245407,0.00006148982,0.00008913282,0.00007659628,0.004209748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007650658,"threshold_uncertainty_score":0.0152123,"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."}}