{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204866,0.0005874276,0.0007607301,0.0004194225,0.0002844838,0.0007869015,0.001960535,0.000711228,0.002917675],"category_scores_gemma":[0.004448511,0.0003956018,0.0004687948,0.0004258422,0.001024328,0.001915465,0.001283106,0.001186237,0.0005015337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007521538,"about_ca_system_score_gemma":0.001007665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003849109,"about_ca_topic_score_gemma":0.004749704,"domain_scores_codex":[0.9995329,0.0001279574,0.0000370693,0.000132224,0.0001164789,0.00005334574],"domain_scores_gemma":[0.9979644,0.001010495,0.0002055708,0.00047861,0.0002329398,0.0001080089],"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":[0.0004229484,0.0002161825,0.002509956,0.0001269073,0.0001057868,0.00009994276,0.0001589295,0.6869864,0.00578124,0.02715348,0.001504625,0.2749337],"study_design_scores_gemma":[0.00002431831,0.00008631983,0.0001552076,0.000004473942,0.000009295642,0.00002339569,0.000005850757,0.9909275,0.001769372,0.006348409,0.0006387564,0.000007153487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04444223,0.0001567302,0.9504001,0.0001496179,0.00003144868,0.00006081085,0.0000410386,0.002460308,0.002257852],"genre_scores_gemma":[0.709849,0.0001020728,0.2857295,0.0001515217,0.00002442573,0.0002132224,0.0001065583,0.0001516276,0.003672077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003849109,"threshold_uncertainty_score":0.009760618,"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."}}