{"id":"W7126375877","doi":"10.21428/594757db.a4de9762","title":"Robust Reinforcement Learning for Linear Temporal Logic Specifications with Finite Trajectory Duration","year":2024,"lang":"en","type":"article","venue":"","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Temporal logic; Linear temporal logic; Reinforcement learning; A priori and a posteriori; Variety (cybernetics); Trajectory; Limit (mathematics); Robot; Robotics","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":[0.002701973,0.0008589878,0.0008005259,0.0005572806,0.0003567832,0.0008822213,0.001114653,0.0008006414,0.001754546],"category_scores_gemma":[0.01344163,0.0004066987,0.000649337,0.0003131892,0.001281669,0.001178215,0.001169135,0.001605964,0.0002398675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00144615,"about_ca_system_score_gemma":0.002173061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005258884,"about_ca_topic_score_gemma":0.006117714,"domain_scores_codex":[0.9986779,0.0004482884,0.000079234,0.0002521307,0.0003714326,0.0001708734],"domain_scores_gemma":[0.990918,0.007125487,0.0008244842,0.0003678309,0.0005226905,0.0002413217],"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":[0.0001221014,0.00005124051,0.0009731718,0.00009102641,0.00002760635,0.0000945711,0.00007594639,0.9560872,0.001666495,0.01583645,0.0003489396,0.02462513],"study_design_scores_gemma":[0.00001176178,0.00002527189,0.00004576117,0.000006465344,0.000003415188,0.000007726147,0.000005630424,0.9928147,0.0005002386,0.006470411,0.0001057615,0.000002887947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04178803,0.000204544,0.9553293,0.0001907637,0.00001957222,0.00008061973,0.00007171152,0.000852327,0.001463137],"genre_scores_gemma":[0.9161391,0.0001128506,0.08176535,0.0001418846,0.00001655322,0.0001523049,0.0001837683,0.0001092592,0.001378961],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005258884,"threshold_uncertainty_score":0.01428956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1403290417013348,"score_gpt":0.3084753156685883,"score_spread":0.1681462739672535,"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."}}