{"id":"W2146823374","doi":"10.7939/r3-b3jb-nw13","title":"Temporal abstraction in temporal-difference networks","year":2006,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalization; Abstraction; Temporal difference learning; Computer science; Variety (cybernetics); Artificial intelligence; Theoretical computer science; Sequence (biology); Machine learning; Mathematics; Reinforcement 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":[0.00003665771,0.00007709291,0.0001148191,0.0001143105,0.00004536707,0.00002720179,0.0005329864,0.00006312875,0.00005509262],"category_scores_gemma":[0.000002450291,0.00009176318,0.00004124535,0.000227128,0.00003303597,0.001184009,0.000183533,0.0001179194,0.000009269756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000154992,"about_ca_system_score_gemma":0.00005102217,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01177814,"about_ca_topic_score_gemma":0.00130819,"domain_scores_codex":[0.9993724,0.00003130721,0.000124592,0.0002294457,0.00009639898,0.0001458366],"domain_scores_gemma":[0.9995207,0.00007304411,0.00008802854,0.000272204,0.000008753954,0.00003724098],"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":[0.00004608236,0.0002383992,0.8988547,0.0000320918,0.00001301592,0.0001077135,0.001538507,0.03109203,0.0001250336,0.05432666,0.005355969,0.008269807],"study_design_scores_gemma":[0.0006990314,0.00004264393,0.3642002,0.00006733798,0.000004397963,0.000006546167,0.0001600761,0.6208881,0.0002033256,0.004949754,0.008491945,0.0002866428],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7829584,0.00004917245,0.1925307,0.001354211,0.0001403448,0.00009332941,4.295484e-7,0.00008371555,0.02278969],"genre_scores_gemma":[0.973728,0.000007212428,0.02087901,0.00005206998,0.0000314285,5.161111e-8,0.00001272448,0.000003839121,0.005285642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5897961,"threshold_uncertainty_score":0.9948025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008525590803184394,"score_gpt":0.1673951647759002,"score_spread":0.1588695739727158,"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."}}