{"id":"W2156211713","doi":"10.1287/moor.1090.0397","title":"Markov Decision Processes with Arbitrary Reward Processes","year":2009,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Regret; Hindsight bias; Reinforcement learning; Mathematical optimization; Mathematics; Q-learning; Markov process; Realization (probability); Function (biology); Trajectory; Markov chain; Process (computing); Computer science; Artificial intelligence","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":[0.003637383,0.001621886,0.00203265,0.0006343289,0.0008739592,0.002313668,0.002828449,0.003166989,0.003607593],"category_scores_gemma":[0.01320907,0.0007958619,0.001187256,0.001074193,0.002702849,0.003141533,0.001995221,0.003448496,0.0006649224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037786,"about_ca_system_score_gemma":0.001622648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005793126,"about_ca_topic_score_gemma":0.003610947,"domain_scores_codex":[0.9971005,0.001156378,0.0001116188,0.0007027158,0.0003938816,0.0005347928],"domain_scores_gemma":[0.9923379,0.005422144,0.0009176061,0.0005052942,0.0003689965,0.0004481119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001892638,0.0001048275,0.0009082179,0.00006004055,0.00005464649,0.0003183068,0.0000916631,0.7284779,0.0005521195,0.2625099,0.0006348015,0.00609842],"study_design_scores_gemma":[0.00004260061,0.00002976945,0.00007822416,0.000005410485,0.00001090739,0.00001737089,0.00000825331,0.9334944,0.0001798146,0.06578854,0.0003328132,0.00001173107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07089176,0.0003431204,0.920385,0.001506747,0.0001054802,0.0001167682,0.0002498372,0.0002135221,0.006187846],"genre_scores_gemma":[0.9053814,0.0005168088,0.08349757,0.0002303442,0.0001621045,0.0003366682,0.0002438345,0.00003944586,0.009591855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005793126,"threshold_uncertainty_score":0.01923656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.205043330395209,"score_gpt":0.5069362652545172,"score_spread":0.3018929348593081,"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."}}