{"id":"W2026641456","doi":"10.1145/1102351.1102463","title":"TD(λ) networks","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Temporal difference learning; Generalization; Formalism (music); Artificial intelligence; Learning network; Machine learning; Theoretical computer science; Algorithm; Reinforcement learning; 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":[0.00008883094,0.00004841724,0.00004486755,0.00001821288,0.00004031953,0.00008313247,0.0004029584,0.00002949582,0.00005416565],"category_scores_gemma":[0.000003321883,0.00003963126,0.00002063598,0.0001085667,0.000009183074,0.0002351412,0.00007773894,0.00006640103,0.0002615384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008260412,"about_ca_system_score_gemma":0.00001400121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006946759,"about_ca_topic_score_gemma":0.000006072549,"domain_scores_codex":[0.9995431,0.00001024973,0.00007667305,0.0001467837,0.00007351602,0.0001496585],"domain_scores_gemma":[0.9996399,0.00001498885,0.00001204618,0.000252954,0.0000224216,0.00005764755],"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":[3.716287e-7,0.00001660345,0.0000536926,4.315391e-7,0.000002173985,0.000001166957,0.00005273116,0.01212938,0.0000321977,0.5209151,0.007439479,0.4593567],"study_design_scores_gemma":[0.00004256463,0.0000100432,0.0001241604,0.000002045669,4.719105e-7,0.000004794497,0.000001170956,0.9870512,0.0001940638,0.002578863,0.009922424,0.00006811969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005286498,0.00008274937,0.9532808,0.002180591,0.00009045201,0.00001638296,3.181084e-8,0.0002369247,0.0435834],"genre_scores_gemma":[0.8491161,0.000009987668,0.1471456,0.001827773,0.000111585,0.000001735368,1.703066e-7,0.000001955859,0.001785074],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9749219,"threshold_uncertainty_score":0.3361634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01440136261469718,"score_gpt":0.2333362374003778,"score_spread":0.2189348747856806,"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."}}