{"id":"W2395778028","doi":"10.7939/r3-dc54-6x83","title":"New representations and approximations for sequential decision making under uncertainty","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Key (lock); Artificial intelligence; Exploit; Observability; Dual (grammatical number); Function (biology); Machine learning; Mathematical optimization; Mathematics","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":[0.003563448,0.0009900886,0.001243058,0.001036514,0.0004756931,0.002570065,0.001683905,0.001396488,0.004191811],"category_scores_gemma":[0.01493109,0.0007784023,0.001155934,0.001444454,0.00182535,0.004099468,0.00266173,0.004369602,0.0006547394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002161106,"about_ca_system_score_gemma":0.001701404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002384358,"about_ca_topic_score_gemma":0.002307966,"domain_scores_codex":[0.9980111,0.0008907382,0.00009965529,0.0002737398,0.0005581717,0.0001664517],"domain_scores_gemma":[0.9950987,0.003261587,0.0004763585,0.0005180862,0.0004388565,0.0002063637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005519471,0.0000415494,0.0003723663,0.00008589659,0.00002601253,0.0000339777,0.0001264308,0.4526076,0.0002838614,0.5187844,0.001311397,0.02627129],"study_design_scores_gemma":[0.000006146571,0.00001114336,0.00002551977,0.00001633318,0.000003650412,0.000007479674,0.00001162963,0.8873152,0.00008501846,0.1115618,0.0009517618,0.000004432646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004840293,0.0002569553,0.9917465,0.0003346581,0.00003296064,0.00002354773,0.00005612015,0.00005774812,0.002651079],"genre_scores_gemma":[0.4010598,0.001266304,0.5881541,0.0002866722,0.0001926983,0.0004648133,0.0004614711,0.0001345314,0.007979557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004191811,"threshold_uncertainty_score":0.01884556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1921472777404747,"score_gpt":0.5278730889014068,"score_spread":0.3357258111609321,"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."}}