{"id":"W4293863172","doi":"10.1109/siu55565.2022.9864806","title":"Autonomous Driving Systems for Decision-Making Under Uncertainty Using Deep Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Markov decision process; Computer science; Artificial intelligence; Action (physics); Process (computing); Observable; Control (management); Markov process; State (computer science); Autonomous agent; Markov chain; Machine learning; Markov model; Mathematics","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":[0.0008888999,0.0006801148,0.0006497143,0.0002289555,0.0003484099,0.000636456,0.0006888782,0.0007037136,0.001241514],"category_scores_gemma":[0.001846143,0.0003349986,0.0004016071,0.0001757975,0.0007276415,0.0005385336,0.0008682188,0.001388184,0.0001427605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008631701,"about_ca_system_score_gemma":0.001399972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009824483,"about_ca_topic_score_gemma":0.007604074,"domain_scores_codex":[0.9997444,0.00007827081,0.00001399544,0.00005657034,0.00005145982,0.00005540723],"domain_scores_gemma":[0.99923,0.0004233122,0.0001119063,0.00004441962,0.0001270342,0.00006341445],"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":[0.00003903483,0.00003885388,0.0006684281,0.00002454696,0.00002363519,0.00004710367,0.00004497065,0.9816239,0.0009655051,0.003436431,0.0002621895,0.01282535],"study_design_scores_gemma":[0.000003145834,0.000009363787,0.00004120691,0.000001378946,0.000001743594,0.000002023563,0.000002066316,0.9987289,0.00009706014,0.001058626,0.00005331432,0.000001174486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1298107,0.0004031737,0.864063,0.0005345487,0.00007562221,0.0000711331,0.0000516876,0.0006332888,0.004356876],"genre_scores_gemma":[0.9804638,0.00006500127,0.01839592,0.00005609394,0.00001204992,0.00004659159,0.00003546618,0.00001390527,0.0009111591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009824483,"threshold_uncertainty_score":0.01953459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04014414957858934,"score_gpt":0.3078733043450014,"score_spread":0.2677291547664121,"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."}}