{"id":"W1499453370","doi":"10.5555/1227505.1227515","title":"Reinforcement Learning with Approximation Spaces","year":2006,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Statistical and Computational Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Reinforcement; Testbed; Artificial intelligence; Set (abstract data type); Space (punctuation); Machine learning; Engineering; Geography","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":[0.00347372,0.001097341,0.001563672,0.0007138331,0.0004527862,0.0017416,0.001586973,0.001322585,0.002560107],"category_scores_gemma":[0.01138416,0.0004125837,0.0009963157,0.0007097175,0.002128966,0.002026923,0.001859924,0.002297722,0.0003737552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001649715,"about_ca_system_score_gemma":0.001131648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00248949,"about_ca_topic_score_gemma":0.001518278,"domain_scores_codex":[0.9975448,0.001368486,0.0001224617,0.0002770075,0.0005440769,0.0001431354],"domain_scores_gemma":[0.994167,0.004376765,0.0003942453,0.0004290561,0.0004363779,0.0001964757],"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":[0.00008900702,0.00006358,0.0006003079,0.0001462335,0.0000950628,0.00006462874,0.0001410841,0.7359882,0.0005218188,0.2207823,0.000683161,0.04082457],"study_design_scores_gemma":[0.00002286829,0.00006013207,0.00005641214,0.00001459541,0.000009636107,0.00001527832,0.00001188323,0.9227118,0.0001858763,0.07567888,0.001224332,0.000008339865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006514841,0.0005327298,0.9897016,0.0002932374,0.00005458607,0.00004017416,0.00002076023,0.0001072521,0.002734869],"genre_scores_gemma":[0.70667,0.00121202,0.2858256,0.0002409224,0.0002137688,0.000394965,0.0001232328,0.00006494181,0.005254473],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00347372,"threshold_uncertainty_score":0.01837099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01069958637320511,"score_gpt":0.2160029224423044,"score_spread":0.2053033360690993,"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."}}