{"id":"W2734058336","doi":"10.1609/socs.v8i1.18421","title":"Non-Markovian Rewards Expressed in LTL: Guiding Search Via Reward Shaping","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Combinatorial Search","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Linear temporal logic; Automaton; Computer science; Markov process; Temporal logic; Mathematical optimization; Planner; State (computer science); Quality (philosophy); Finite-state machine; Theoretical computer science; Artificial intelligence; Mathematics; Algorithm","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":[0.00119405,0.0006920914,0.0004774033,0.0003901056,0.0004442387,0.001089512,0.001216133,0.0008920906,0.002528832],"category_scores_gemma":[0.006395522,0.0004360209,0.0007341806,0.0003934482,0.001319316,0.001380695,0.001186764,0.001722088,0.0004153552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009874748,"about_ca_system_score_gemma":0.002953161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005760891,"about_ca_topic_score_gemma":0.007251036,"domain_scores_codex":[0.9992613,0.000260271,0.0000505116,0.0001231367,0.0001929284,0.0001117528],"domain_scores_gemma":[0.9971702,0.001960547,0.0002568685,0.000261761,0.0002314674,0.0001192156],"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":[0.000165046,0.00009844316,0.0008459283,0.0001346491,0.0000333378,0.0001762164,0.0002280699,0.8655651,0.006333282,0.07145265,0.001107599,0.05385974],"study_design_scores_gemma":[0.00002058397,0.00003438525,0.00003598481,0.00001244757,0.00001023786,0.0000190363,0.00001623561,0.9676693,0.003147324,0.02785897,0.001167721,0.000007874672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01563658,0.00008654185,0.980171,0.0002388581,0.00002895244,0.0000697854,0.00006588587,0.001377338,0.002325061],"genre_scores_gemma":[0.6170176,0.0002080221,0.3792002,0.0002120904,0.00002137282,0.0002627689,0.0001739331,0.0002924647,0.002611511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005760891,"threshold_uncertainty_score":0.0114547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0432312004337493,"score_gpt":0.3062496548638452,"score_spread":0.2630184544300959,"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."}}