{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002852846,0.0008560957,0.0006189278,0.0005622145,0.0005730974,0.001747343,0.001338337,0.0008750975,0.003350336],"category_scores_gemma":[0.008090721,0.0005173255,0.00112291,0.0007538411,0.002094002,0.002665948,0.001703262,0.001846606,0.0004341502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001586553,"about_ca_system_score_gemma":0.003620665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003037399,"about_ca_topic_score_gemma":0.004189306,"domain_scores_codex":[0.997491,0.001044557,0.0001601229,0.0003845273,0.0007447887,0.0001749783],"domain_scores_gemma":[0.9951038,0.003737218,0.0003550956,0.0003795446,0.0002670512,0.0001573034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000131453,0.00007196478,0.0004929677,0.0002296018,0.00005151986,0.0001494945,0.0002562901,0.3906796,0.001979043,0.545961,0.001570184,0.05842682],"study_design_scores_gemma":[0.00005327458,0.00006680785,0.0001430346,0.00004036877,0.00002300312,0.00006252289,0.00003647338,0.7106074,0.002309883,0.2784242,0.008210194,0.00002286369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007782176,0.0002308931,0.9855924,0.0002798346,0.00003197437,0.00009580952,0.00009742974,0.0003209503,0.005568493],"genre_scores_gemma":[0.3203368,0.0006625506,0.6739384,0.000134517,0.0000437077,0.0003502244,0.0002984238,0.0001209726,0.004114474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003350336,"threshold_uncertainty_score":0.01508743,"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."}}