{"id":"W2141050197","doi":"10.4304/jcp.2.1.12-19","title":"Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization","year":2007,"lang":"en","type":"article","venue":"Journal of Computers","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Dynamic programming; Computer science; Sharpe ratio; Reinforcement learning; Mathematical optimization; Portfolio; Markov decision process; Kernel (algebra); Controller (irrigation); Artificial intelligence; Markov process; Mathematics; Algorithm; Finance","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":[],"consensus_categories":[],"category_scores_codex":[0.0007874601,0.0001313873,0.0001937699,0.000311655,0.00009142764,0.0001855328,0.000644803,0.00004413921,5.868783e-7],"category_scores_gemma":[0.00002579117,0.0001106421,0.00007191102,0.0004567684,0.00001957318,0.000466461,0.00007562285,0.0001299111,0.00000248392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000127006,"about_ca_system_score_gemma":0.00007467023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001445446,"about_ca_topic_score_gemma":8.166475e-7,"domain_scores_codex":[0.9986134,0.00001510269,0.0004990953,0.0001789253,0.0004031671,0.0002903582],"domain_scores_gemma":[0.9984619,0.00009822647,0.0006068347,0.0002554059,0.000419002,0.0001586038],"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":[0.00003899348,0.00003389617,0.0001586699,0.00001910188,0.00002445445,0.000008661911,0.0002492124,0.9235932,0.00007063508,0.0009410754,0.00007381345,0.07478832],"study_design_scores_gemma":[0.0005226686,0.0008975678,0.0002208468,0.00007888707,0.00001820396,0.0001225639,0.00003783287,0.9949246,0.000147182,0.00004181599,0.002845224,0.0001425778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001874642,0.00001537295,0.9967886,0.0003586042,0.0003375121,0.0004915721,1.72774e-7,0.00004798517,0.0000855879],"genre_scores_gemma":[0.1412042,0.000003703312,0.8584443,0.0001963369,0.00008789266,0.000006228786,0.000002392519,0.0000143854,0.00004063443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1393295,"threshold_uncertainty_score":0.4511853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007554112725446023,"score_gpt":0.260925085287421,"score_spread":0.253370972561975,"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."}}