{"id":"W2072164538","doi":"10.1142/s0218213006002990","title":"AGGREGATION OF MULTIPLE REINFORCEMENT LEARNING ALGORITHMS","year":2006,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Learning classifier system; Robustness (evolution); Artificial intelligence; Instance-based learning; Machine learning; Algorithm; Unsupervised learning; Robot learning; Fault tolerance; Architecture; Distributed computing; Robot","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":[0.002031568,0.0008557938,0.001310193,0.0005627734,0.000426317,0.0008234073,0.001233941,0.0006744874,0.00186145],"category_scores_gemma":[0.003942616,0.0003648858,0.0005583841,0.0004252748,0.0005728651,0.001070162,0.001600196,0.001001912,0.0003674874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006442693,"about_ca_system_score_gemma":0.0007053306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001893208,"about_ca_topic_score_gemma":0.001609518,"domain_scores_codex":[0.9986857,0.0003797216,0.00009749055,0.0002804828,0.0003972691,0.0001593699],"domain_scores_gemma":[0.9980432,0.0007099272,0.0002442713,0.0003521309,0.0005009227,0.0001495642],"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":[0.0002449896,0.0001756443,0.002000713,0.0001150881,0.0001647232,0.0001862321,0.0001376211,0.7530064,0.007997213,0.007503864,0.001190509,0.227277],"study_design_scores_gemma":[0.0000224265,0.0001082837,0.0002402558,0.000006829203,0.00001995208,0.00003576862,0.00001053075,0.9937056,0.001567499,0.003408482,0.0008653913,0.000008908991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07982716,0.0004664074,0.9134955,0.0002233598,0.0001426256,0.0001481787,0.00002546103,0.001427833,0.004243445],"genre_scores_gemma":[0.9054611,0.0001295676,0.0919989,0.00007319022,0.00005516295,0.0001211483,0.00004003687,0.00003744892,0.002083424],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002031568,"threshold_uncertainty_score":0.01074409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04119386503159132,"score_gpt":0.3033805911273944,"score_spread":0.262186726095803,"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."}}