{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002647992,0.000102781,0.0001583095,0.000420168,0.0003892392,0.0003339103,0.0003571005,0.00006946104,0.0007876315],"category_scores_gemma":[0.004073288,0.00007549861,0.000076624,0.0008484845,0.00009689793,0.000507434,0.0001802559,0.0001055337,0.00006119326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007131716,"about_ca_system_score_gemma":0.000123678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005432581,"about_ca_topic_score_gemma":0.0005720553,"domain_scores_codex":[0.9974199,0.0000426663,0.0005350308,0.0005079323,0.00114311,0.00035139],"domain_scores_gemma":[0.9922308,0.006588472,0.0001076384,0.0004461075,0.000445322,0.0001816862],"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":[0.0001527657,0.00002983321,0.0005092761,0.000002869185,0.00001591769,0.000003682891,0.0003215147,0.0293308,0.0003603969,0.0289748,0.01310038,0.9271978],"study_design_scores_gemma":[0.0009340961,0.00005449147,0.007398008,0.00001181878,0.000007314975,0.00001978215,0.002702682,0.09289081,0.0005511836,0.8783153,0.01694267,0.0001719052],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005836513,0.0000461735,0.9895475,0.0007220869,0.0002085821,0.0004823487,0.00001384907,0.00004731886,0.003095646],"genre_scores_gemma":[0.3939266,0.000005237769,0.5943244,0.0001470434,0.0002084612,0.00001677187,0.000006860484,0.00001362347,0.01135102],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9270259,"threshold_uncertainty_score":0.8624012,"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."}}