{"id":"W1490038383","doi":"10.48550/arxiv.1301.0606","title":"Anytime State-Based Solution Methods for Decision Processes with non-Markovian Rewards","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Markov decision process; Computer science; Representation (politics); Embedding; Markov process; Exploit; State space; Partially observable Markov decision process; Mathematical optimization; Computation; State (computer science); Theoretical computer science; Translation (biology); Artificial intelligence; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.001392185,0.0001756056,0.0001765066,0.0002065893,0.0002349587,0.00006033818,0.0007423406,0.00008511788,0.000007633269],"category_scores_gemma":[0.0005166144,0.0001652893,0.00006080632,0.001204056,0.00008737517,0.001672287,0.000113067,0.0001058215,0.00002108538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001701903,"about_ca_system_score_gemma":0.0002279113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001874929,"about_ca_topic_score_gemma":0.00001092255,"domain_scores_codex":[0.9986599,0.0001647308,0.000176298,0.0004724033,0.00008945306,0.0004372087],"domain_scores_gemma":[0.9980277,0.0006172052,0.0001905263,0.0006571563,0.0003236171,0.0001837799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003986102,0.002140059,0.06936919,0.001607473,0.0002735799,0.00004744107,0.004002841,0.1581805,0.01076386,0.2202213,0.001565697,0.5278419],"study_design_scores_gemma":[0.001012638,0.0004192586,0.004272417,0.00008959734,0.00005097506,0.000006103791,0.00005750937,0.9592529,0.0262161,0.005164566,0.002994521,0.0004633965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03563217,0.00003594263,0.9630915,0.00002826951,0.0002345281,0.0003709361,0.000003778847,0.0001601468,0.0004427136],"genre_scores_gemma":[0.4703833,0.000006342118,0.5294296,0.00004246699,0.00001980367,0.000002706035,0.000002143684,0.000008856954,0.000104807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8010725,"threshold_uncertainty_score":0.6740301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07334018311488119,"score_gpt":0.2621029346985852,"score_spread":0.188762751583704,"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."}}