{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005981836,0.0002159745,0.000483933,0.001278002,0.0006492659,0.0007381237,0.001850633,0.0001090678,0.000551271],"category_scores_gemma":[0.0491695,0.0001346057,0.00005413499,0.006631904,0.0005196418,0.001168688,0.0002331456,0.0005318077,0.0002831775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007448259,"about_ca_system_score_gemma":0.002212335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001257019,"about_ca_topic_score_gemma":0.0003074862,"domain_scores_codex":[0.9910055,0.0002257569,0.001019356,0.0006615821,0.006440941,0.000646831],"domain_scores_gemma":[0.9822537,0.00698715,0.0001032933,0.001283109,0.009140673,0.0002321256],"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":[0.003492234,0.02207252,0.003188232,0.006688403,0.0004561912,0.0007507571,0.05096899,0.1515315,0.01873965,0.04335505,0.07353304,0.6252235],"study_design_scores_gemma":[0.003538978,0.005989485,0.003038308,0.002677854,0.00003969661,0.0003287962,0.01844151,0.06616969,0.1143317,0.7757308,0.008209879,0.001503256],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3998399,0.0013592,0.5688211,0.004250044,0.00006961729,0.002887183,0.00009140901,0.0001466088,0.02253491],"genre_scores_gemma":[0.6772392,0.000274021,0.3175356,0.00003598225,0.00008609535,0.0001142259,0.00001029622,0.00003215648,0.00467244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7323758,"threshold_uncertainty_score":0.9588398,"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."}}