{"id":"W2141650360","doi":"10.1109/icsmc.2004.1399805","title":"Reinforcement learning and aggregation","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Artificial intelligence; Q-learning; Machine learning; Computation; Learning classifier system; Algorithm","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":[0.001944549,0.001046143,0.001613355,0.000721601,0.000760858,0.002140947,0.001443551,0.001309302,0.004661807],"category_scores_gemma":[0.006956087,0.0003666526,0.0008637502,0.0009924647,0.001972414,0.00227215,0.002289256,0.001596676,0.0007188041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001705577,"about_ca_system_score_gemma":0.001386323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003872384,"about_ca_topic_score_gemma":0.002150124,"domain_scores_codex":[0.9979903,0.0006105948,0.0001408773,0.0004938099,0.0005847038,0.0001797456],"domain_scores_gemma":[0.9971209,0.001358669,0.0004468502,0.0003788097,0.0005175074,0.0001771574],"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":[0.0001051718,0.0001151836,0.00163361,0.0003202845,0.000184447,0.0001975711,0.0001893624,0.5031036,0.001807634,0.3479144,0.005725288,0.1387035],"study_design_scores_gemma":[0.00004578231,0.0001111005,0.0004693382,0.00004612308,0.00004450312,0.0001223286,0.0000417807,0.6518942,0.0009714667,0.3318643,0.01436017,0.00002897533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01124891,0.002931055,0.9635499,0.0009867058,0.0002649945,0.0001305381,0.00008793767,0.0005642583,0.02023567],"genre_scores_gemma":[0.7615851,0.004109654,0.2156709,0.0005581524,0.0006410971,0.0005239348,0.0002628655,0.0001705416,0.01647774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004661807,"threshold_uncertainty_score":0.01559526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01118141094089683,"score_gpt":0.2448448695310357,"score_spread":0.2336634585901388,"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."}}