{"id":"W2133180954","doi":"10.1613/jair.1676","title":"Decision-Theoretic Planning with non-Markovian Rewards","year":2006,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; Australian Government; National ICT Australia","keywords":"Markov decision process; Computer science; Markov process; Partially observable Markov decision process; Heuristic; Probabilistic logic; Planner; Mathematical optimization; Decision problem; Process (computing); Function (biology); Artificial intelligence; Mathematics; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006385134,0.0001642231,0.0002835183,0.0007851908,0.0004616969,0.0005846304,0.001540025,0.0001046401,0.00005384284],"category_scores_gemma":[0.0005118882,0.0001197943,0.0001038976,0.001420383,0.0002656936,0.0005773912,0.000177951,0.00108028,0.00008317517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001235439,"about_ca_system_score_gemma":0.0005819289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001092044,"about_ca_topic_score_gemma":0.00002068085,"domain_scores_codex":[0.9962333,0.0002828832,0.0007902759,0.0003122714,0.001687048,0.0006942073],"domain_scores_gemma":[0.9960357,0.00185099,0.0002816543,0.000451644,0.001153259,0.0002267338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001218662,0.0005490212,0.006628259,0.00009486771,0.00009006105,0.003586655,0.005005226,0.1536491,0.005537347,0.1296755,0.01201518,0.6819502],"study_design_scores_gemma":[0.000227387,0.004041043,0.001423906,0.002548963,0.00002438655,0.001049885,0.001907746,0.2935932,0.07134192,0.6181481,0.004946143,0.0007472781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009229,0.000370972,0.8945156,0.00102339,0.0002887651,0.00010881,8.693661e-7,0.00002542631,0.002743301],"genre_scores_gemma":[0.9057747,0.00001896761,0.09360936,0.00003298072,0.0004271007,0.000002766715,5.627056e-7,0.00001534808,0.0001181803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8048518,"threshold_uncertainty_score":0.5637604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06525791475197834,"score_gpt":0.3788264025247418,"score_spread":0.3135684877727634,"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."}}