{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002135796,0.001077642,0.001467381,0.0008014754,0.0006658254,0.002316823,0.001704383,0.002921446,0.007972224],"category_scores_gemma":[0.006709349,0.0008187746,0.001233421,0.001300931,0.001900131,0.002072623,0.001280517,0.00286736,0.0007070596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003005769,"about_ca_system_score_gemma":0.003150671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008952209,"about_ca_topic_score_gemma":0.006659934,"domain_scores_codex":[0.9990736,0.0003649074,0.00004030428,0.000183016,0.0001903995,0.0001477676],"domain_scores_gemma":[0.9973911,0.001897214,0.0002961359,0.00007995687,0.0002167746,0.0001187292],"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":[0.00002332238,0.00002513116,0.0002366658,0.00006788289,0.00002327088,0.00008694053,0.00006551398,0.7580675,0.0002111126,0.2359239,0.000980392,0.00428839],"study_design_scores_gemma":[0.00001243505,0.00001116317,0.00005920447,0.00001375461,0.000006385321,0.00001627248,0.00001527534,0.924474,0.00005068796,0.07447466,0.0008587793,0.000007376986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009110318,0.0004708178,0.9777316,0.001521798,0.00007957486,0.00004699222,0.0002494542,0.00008063151,0.01070874],"genre_scores_gemma":[0.7713246,0.001958769,0.197609,0.0003743457,0.0002134311,0.0006899716,0.0004808,0.00007289783,0.02727618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008952209,"threshold_uncertainty_score":0.02666968,"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."}}