{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004411757,0.00009900195,0.0001504648,0.0002364938,0.00007737794,0.0001381326,0.0009467818,0.00004554896,0.00004966975],"category_scores_gemma":[0.0001983996,0.00009316202,0.0001414742,0.0002620741,0.00006921451,0.0009092891,0.0001053584,0.0001810873,0.00002947199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009105985,"about_ca_system_score_gemma":0.0001007649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008811663,"about_ca_topic_score_gemma":0.000008284293,"domain_scores_codex":[0.9980469,0.0000394403,0.000948406,0.0001433157,0.0006836814,0.0001382981],"domain_scores_gemma":[0.9977067,0.000230017,0.0007380054,0.000146496,0.001131267,0.00004754671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002684085,0.0002133566,0.0003956489,0.000003038711,0.00004730869,0.00001725022,0.0002220894,0.2483941,0.007243403,0.2960344,0.000172655,0.4472299],"study_design_scores_gemma":[0.000122377,0.00024437,0.001458454,0.00008868967,0.00001124512,0.0001088136,0.0002062655,0.713887,0.1790493,0.09989379,0.004738632,0.0001910883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01363551,0.00008961613,0.9837059,0.001036873,0.0006533962,0.00008312066,0.000002740369,0.0000213462,0.0007715028],"genre_scores_gemma":[0.930924,0.00004378688,0.0683669,0.00003385989,0.00048074,0.000004604373,0.000008367887,0.000005245323,0.0001324677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9172885,"threshold_uncertainty_score":0.3799037,"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."}}