{"id":"W2900798285","doi":"10.65109/loxq3741","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Domain (mathematical analysis); Dual (grammatical number); Markov decision process; Function (biology); Lexicographical order; Collision; Markov process; Machine learning; Computer security; Engineering; 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"],"consensus_categories":[],"category_scores_codex":[0.0005184576,0.0006550378,0.0006039941,0.0003468756,0.0002522563,0.0008187518,0.002283045,0.0003467366,0.00009571503],"category_scores_gemma":[0.0001464729,0.0005524237,0.0001856957,0.000323164,0.00007671703,0.0005140052,0.004494876,0.002072118,0.0004514179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000428791,"about_ca_system_score_gemma":0.0003757501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001121534,"about_ca_topic_score_gemma":0.0000192814,"domain_scores_codex":[0.9961822,0.0001658935,0.0006001622,0.001267491,0.0009950122,0.0007892077],"domain_scores_gemma":[0.9967346,0.0002087998,0.0007047856,0.001835411,0.0003300326,0.0001863441],"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":[0.000006135645,0.00001760706,0.01223291,0.00009050852,0.0001598447,0.0000150534,0.002265994,0.9808812,0.00001475561,0.003421863,0.0002549639,0.0006392131],"study_design_scores_gemma":[0.0006202883,0.0003197786,0.00226762,0.0003175011,0.00003278976,0.00000914514,0.0001763127,0.9935004,0.0002336926,0.00002035695,0.001707381,0.0007947242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004351317,0.00005387791,0.9587708,0.0001104573,0.0009182039,0.0009673595,9.001869e-8,0.0008260864,0.03791796],"genre_scores_gemma":[0.7881457,0.00003301237,0.1762497,0.0002017362,0.0001132721,0.00006733445,0.00002769146,0.00006501139,0.03509648],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7877106,"threshold_uncertainty_score":0.9996927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01674804821501111,"score_gpt":0.2469498928797251,"score_spread":0.230201844664714,"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."}}