{"id":"W4225574046","doi":"10.1287/mnsc.2021.4194","title":"Analytical Solution to a Discrete-Time Model for Dynamic Learning and Decision Making","year":2022,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Partially observable Markov decision process; Discrete time and continuous time; Computer science; Mathematical optimization; Markov decision process; Dynamic decision-making; Set (abstract data type); Time horizon; Bellman equation; Constant (computer programming); Markov process; Process (computing); Markov chain; Mathematics; Markov model; Artificial intelligence; Machine learning","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.007147442,0.0001132007,0.0001685757,0.00106717,0.001942888,0.0004949909,0.001250288,0.00001329162,0.0001488761],"category_scores_gemma":[0.001658395,0.00009621544,0.00005206043,0.002807769,0.0002763932,0.0005386637,0.003225617,0.0001612413,0.00006973559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000333915,"about_ca_system_score_gemma":0.00004290313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001185626,"about_ca_topic_score_gemma":0.000003298119,"domain_scores_codex":[0.9947984,0.00005890799,0.0003346231,0.001004141,0.003216972,0.0005869474],"domain_scores_gemma":[0.9986383,0.000592379,0.00008695554,0.0003915448,0.0001324778,0.0001583608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008581456,0.00002111867,0.0002166902,0.000003098738,0.00000321275,0.000005991727,0.0002033092,0.608436,0.0001662441,0.001360311,0.0005235977,0.3889745],"study_design_scores_gemma":[0.0002021352,0.0001187405,0.001427609,0.000008135923,0.000005128895,0.000002877463,0.0005297196,0.9495514,0.000002897895,0.04544033,0.002586262,0.0001247797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0385487,0.00001767032,0.9591754,0.0006486643,0.00009352442,0.0005948658,0.000008786834,0.00003801702,0.0008743372],"genre_scores_gemma":[0.8761258,0.000003030003,0.1173167,0.0001168388,0.000009288166,0.0001178009,0.000001239104,0.00000938396,0.006299971],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8418587,"threshold_uncertainty_score":0.9993564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06880974970414613,"score_gpt":0.4639385086242527,"score_spread":0.3951287589201066,"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."}}