{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001186792,0.0001089081,0.00009905733,0.00007482338,0.0001775659,0.000361797,0.0002409159,0.00002064318,0.00003971625],"category_scores_gemma":[0.0000113329,0.00008335957,0.00002197158,0.0002032559,0.00003044101,0.0009048261,0.00009586842,0.00009360667,0.0001770176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000498889,"about_ca_system_score_gemma":0.00003477076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004809687,"about_ca_topic_score_gemma":0.000002125806,"domain_scores_codex":[0.9989572,0.00001418133,0.0002914304,0.0001194924,0.0004052864,0.0002124234],"domain_scores_gemma":[0.9995446,0.00007899568,0.000113402,0.0001462104,0.00006693719,0.00004990974],"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":[0.000008853525,0.00002447188,0.0003894252,0.00003663277,0.00001149997,0.000002119034,0.0007049811,0.3287224,0.00001601967,0.6585971,0.0004197365,0.01106674],"study_design_scores_gemma":[0.00032831,0.0001324511,0.00116893,0.00002799145,0.00000439618,0.00001228043,0.0001130791,0.9818024,0.0001453415,0.01337532,0.002743651,0.000145862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01157141,0.000008740927,0.9632296,0.0003490461,0.0000467169,0.0001387389,5.0039e-7,0.0001554888,0.02449979],"genre_scores_gemma":[0.8013678,8.346701e-7,0.1979209,0.0002561613,0.00003137602,0.00002410984,0.00002904472,0.000003821547,0.0003660047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7897964,"threshold_uncertainty_score":0.3488817,"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."}}