{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002689851,0.0002029098,0.0002639154,0.0002413691,0.0001794826,0.0003572887,0.003466487,0.0001444787,0.00002090391],"category_scores_gemma":[0.0006937144,0.0001858596,0.0001493849,0.001090127,0.00009620345,0.0008036686,0.001664973,0.0004723988,0.0000164528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005705086,"about_ca_system_score_gemma":0.0002003766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001621876,"about_ca_topic_score_gemma":0.000002049774,"domain_scores_codex":[0.9963443,0.0000738926,0.0005911122,0.0006559202,0.001896529,0.0004382819],"domain_scores_gemma":[0.9977181,0.000194127,0.0001947547,0.0004071331,0.001379857,0.0001060286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001516239,0.0003211859,0.005558209,0.00009510909,0.00004636274,0.000006128371,0.001633969,0.0002534516,0.6469468,0.3418897,0.0004301817,0.002667311],"study_design_scores_gemma":[0.0009897404,0.0001287996,0.003246268,0.0003791031,0.00000458158,0.00001647081,0.0001308979,0.04507723,0.9337495,0.01463273,0.001406566,0.0002381189],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9298789,0.0000324062,0.005958208,0.0123934,0.009673551,0.0006845643,0.000008190449,0.0001255727,0.04124523],"genre_scores_gemma":[0.9809046,0.00003590183,0.01822399,0.0001604919,0.0003736033,0.0000417659,0.000002379429,0.00002487182,0.0002323424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.327257,"threshold_uncertainty_score":0.7579135,"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."}}