{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001038141,0.0002778399,0.0003095942,0.0003051674,0.005523004,0.0009815549,0.002644013,0.0000741308,0.00004476012],"category_scores_gemma":[0.00006937193,0.0003151561,0.00008074404,0.0009493096,0.000191233,0.0005223489,0.002155494,0.000700154,0.000005008015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004088839,"about_ca_system_score_gemma":0.0006033037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000477275,"about_ca_topic_score_gemma":0.000007438064,"domain_scores_codex":[0.9974675,0.0001903823,0.0007328736,0.0006167292,0.0005237685,0.0004688037],"domain_scores_gemma":[0.9963074,0.0009793433,0.0006644062,0.001478782,0.0004481246,0.0001219255],"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":[0.000005318479,0.00003820801,0.00009321538,0.00003988202,0.00002326575,2.24893e-7,0.0007314609,0.8440272,0.0001470946,0.06744343,0.00002117376,0.08742952],"study_design_scores_gemma":[0.0002307284,0.00009389446,0.00003388359,0.0001269603,0.00004260358,0.0000273113,0.00286968,0.9777806,0.000004523553,0.003059692,0.01536952,0.0003605624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004128704,0.001906694,0.9946258,0.000423363,0.00006138229,0.001061835,0.000002981041,0.000296202,0.001208844],"genre_scores_gemma":[0.9201249,0.0001581144,0.07715924,0.0001448455,0.00003502452,0.001954645,0.00005779444,0.00003105852,0.0003343657],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9197121,"threshold_uncertainty_score":0.99993,"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."}}