{"id":"W2967563764","doi":"10.3389/frobt.2020.00034","title":"Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures","year":2020,"lang":"en","type":"preprint","venue":"Frontiers in Robotics and AI","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation; Alberta Machine Intelligence Institute","keywords":"Artificial intelligence; Computer science; Machine learning; Adaptation (eye); Robot; Model predictive control; Property (philosophy); Representation (politics); Ranging; Robotics; Process (computing); Bar (unit); Incremental learning; Feature (linguistics); Control (management)","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000363195,0.0003539732,0.0005834018,0.0002826066,0.0001048479,0.0002610672,0.001640444,0.0001656129,5.362424e-7],"category_scores_gemma":[0.0001925057,0.0002821219,0.00008459532,0.0002597567,0.0002585655,0.000113546,0.003174707,0.0006658914,1.331257e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008827504,"about_ca_system_score_gemma":0.0001952227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004680774,"about_ca_topic_score_gemma":0.0002116818,"domain_scores_codex":[0.9979622,0.000157436,0.000530587,0.000796192,0.0002377172,0.0003158049],"domain_scores_gemma":[0.9982268,0.0003147726,0.0003543366,0.0009046794,0.0001030919,0.00009629122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004032794,0.0006163414,0.3943714,0.001853604,0.0008891601,0.00004943996,0.01948009,0.05522946,0.0002116786,0.02267,0.273231,0.2309946],"study_design_scores_gemma":[0.0004230135,0.0003783049,0.02328336,0.0008414167,0.0000802211,0.000002487101,0.0001289288,0.9376555,0.0007020171,0.03463846,0.001359258,0.0005070257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005455621,0.0002953181,0.9910507,0.0007851917,0.0006979695,0.0009209621,0.0005397353,0.0001498937,0.0001046582],"genre_scores_gemma":[0.3253819,0.0001264601,0.6739434,0.000142177,0.0000743165,0.00009911283,0.000154527,0.00002427114,0.00005382485],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8824261,"threshold_uncertainty_score":0.9999631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.079332224183132,"score_gpt":0.2991319657239803,"score_spread":0.2197997415408482,"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."}}