{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009306904,0.000109186,0.0001255986,0.000184151,0.0000846808,0.00004685577,0.0004576277,0.00005680079,0.00005733439],"category_scores_gemma":[0.0001272489,0.000102318,0.0000608145,0.0003953196,0.00003646644,0.0002501898,0.0001073086,0.000155136,0.00004541705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000565135,"about_ca_system_score_gemma":0.00005865583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002555214,"about_ca_topic_score_gemma":0.000001951591,"domain_scores_codex":[0.9985826,0.00002577095,0.0004188665,0.0002012676,0.000492261,0.0002792267],"domain_scores_gemma":[0.9990154,0.0001636814,0.000236342,0.0003603117,0.0001542242,0.00007004885],"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":[0.000004329246,0.000008883448,0.001017616,0.00001328619,0.000007256532,0.000002765182,0.0001481737,0.9647185,0.0004379153,0.01100049,0.00003328327,0.02260753],"study_design_scores_gemma":[0.0003079695,0.0001910767,0.0005768627,0.00002574424,0.000003272701,0.000001238118,0.00002972299,0.943746,0.05298908,0.00004199617,0.001974605,0.0001124066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001523536,0.00001295598,0.9783222,0.00007936366,0.0001925318,0.0001218901,2.179286e-8,0.000192032,0.01955544],"genre_scores_gemma":[0.8447554,0.000002491407,0.1524939,0.0001375332,0.00002831683,0.000001558732,0.000004294239,0.000007019686,0.002569441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8432319,"threshold_uncertainty_score":0.4172408,"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."}}