{"id":"W2136617285","doi":"10.1109/icsmc.2007.4414024","title":"Aggregation of tiling-based reinforcement learning algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Aggregate (composite); Architecture; Artificial intelligence; Function (biology); Stability (learning theory); Instance-based learning; Competitive learning; Algorithm; Machine learning; Unsupervised learning","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":[0.001932836,0.0007870218,0.001506257,0.0006926321,0.0004368469,0.0008552204,0.001137723,0.0006658349,0.002668949],"category_scores_gemma":[0.005375023,0.0003958923,0.0006100188,0.0004996217,0.0009135202,0.001341709,0.001889135,0.001010017,0.0004363976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007462999,"about_ca_system_score_gemma":0.000621838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002165664,"about_ca_topic_score_gemma":0.001682563,"domain_scores_codex":[0.9988672,0.0003413332,0.00009103586,0.0002678527,0.0003046391,0.0001279993],"domain_scores_gemma":[0.9976299,0.001075307,0.0002650866,0.0003626067,0.0005205735,0.000146541],"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":[0.0001209392,0.00007830176,0.001189142,0.00006151541,0.0000715298,0.00007853495,0.0001272786,0.8721768,0.003208364,0.007677966,0.0007599849,0.1144497],"study_design_scores_gemma":[0.00001144472,0.00004967387,0.00007837897,0.000004421468,0.000007219056,0.0000130672,0.000006291951,0.9951565,0.00069045,0.003505851,0.0004724279,0.000004311539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04560184,0.0002917563,0.9494561,0.0001274394,0.00008787457,0.00009256371,0.0000248854,0.0009256807,0.003391864],"genre_scores_gemma":[0.8470404,0.0001829137,0.1498472,0.000119176,0.0000572045,0.0001612014,0.00008269073,0.00009014529,0.002419053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002668949,"threshold_uncertainty_score":0.0102219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789302460037047,"score_gpt":0.2669956302511332,"score_spread":0.2491026056507628,"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."}}