{"id":"W2222917154","doi":"","title":"Integrating Representation Learning and Temporal Difference Learning: A Matrix Factorization Approach","year":2014,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Temporal difference learning; Artificial intelligence; Feature learning; Representation (politics); Formalism (music); Semi-supervised learning; Factorization; Machine learning; Mathematical optimization; Algorithm; Mathematics","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":[0.0002789061,0.0001674422,0.0001610732,0.0001086455,0.0003181543,0.0002019357,0.0001028963,0.00006139003,0.0003077592],"category_scores_gemma":[0.0001525387,0.0001557415,0.00004633356,0.0002262498,0.00008184036,0.0001510228,0.0000347715,0.0004797773,0.00003743865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002513702,"about_ca_system_score_gemma":0.00004841392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007364414,"about_ca_topic_score_gemma":0.000003412983,"domain_scores_codex":[0.998529,0.000201783,0.0003210355,0.0003883947,0.0003806243,0.0001792261],"domain_scores_gemma":[0.9991679,0.0001842899,0.000189946,0.00006572468,0.0003080456,0.00008404749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002925311,0.00006106569,0.00819443,0.000004612051,0.000008759882,6.791439e-8,0.0003124128,0.01084144,0.002170839,0.7670682,0.00001024748,0.2112987],"study_design_scores_gemma":[0.0000404513,0.000099659,0.0007778719,0.00002607094,0.000005853606,9.280455e-7,0.001146245,0.8865355,0.003831985,0.1069475,0.0003881025,0.0001998521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07297154,0.000005246255,0.9001943,0.0002414392,0.0001215821,0.0001607935,0.000002826207,0.00007083708,0.0262314],"genre_scores_gemma":[0.9966089,0.000006602946,0.001633265,0.00002423832,0.0003505288,0.00002758671,0.0001220567,0.00001223304,0.001214657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9236373,"threshold_uncertainty_score":0.6350954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.092088676256048,"score_gpt":0.3547959311461222,"score_spread":0.2627072548900742,"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."}}