{"id":"W2097778153","doi":"10.1145/1390156.1390278","title":"Sample-based learning and search with permanent and transient memories","year":2008,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Sample (material); Function (biology); Artificial intelligence; Transient (computer programming); Q-learning; Matching (statistics); Bellman equation; Machine learning; Mathematical optimization; Mathematics; Operating system","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":[0.0001205171,0.00008264534,0.00008811391,0.00005245143,0.0002386641,0.00007758645,0.0001306817,0.00002078482,0.00002239565],"category_scores_gemma":[0.00001881637,0.00006045253,0.0000108477,0.0001277814,0.0002451692,0.000179595,0.00005127522,0.0001019299,0.000005885024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009894045,"about_ca_system_score_gemma":0.00004824763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001440187,"about_ca_topic_score_gemma":0.00004474646,"domain_scores_codex":[0.9992278,0.00003564591,0.00009289496,0.0002493445,0.0002123711,0.0001820084],"domain_scores_gemma":[0.9995499,0.0001765871,0.00001393193,0.0001211495,0.00005350965,0.00008494787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001897745,0.0002725047,0.4794741,0.0001425047,0.00007236835,0.0004031643,0.08721174,0.01522389,0.004716426,0.08856848,0.0005808242,0.3231442],"study_design_scores_gemma":[0.0005979174,0.001772041,0.05336554,0.00007362545,0.00001505912,0.0004667167,0.002893642,0.7723733,0.1431258,0.0009559497,0.02344853,0.0009118552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4733297,0.0000673506,0.5250256,0.0007609936,0.00001698612,0.00006344797,2.419008e-7,0.0000710824,0.0006646125],"genre_scores_gemma":[0.9421909,0.00004147779,0.05736319,0.0001232758,0.00001293051,0.0000041315,4.604135e-7,0.000004584602,0.000259071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7571494,"threshold_uncertainty_score":0.2465183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04074702411668039,"score_gpt":0.275774518047986,"score_spread":0.2350274939313056,"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."}}