{"id":"W2401533533","doi":"","title":"Off-policy TD(λ) with a true online equivalence","year":2014,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Stability and Control of Uncertain Systems","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Online algorithm; Computer science; Equivalence (formal languages); Generalization; TRACE (psycholinguistics); Function approximation; Online learning; Algorithm; Function (biology); Artificial intelligence; Machine learning; Mathematics; Discrete mathematics; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005592987,0.0003249999,0.000439426,0.0002745884,0.00007780109,0.00007958747,0.0004951005,0.0001430516,0.0001157715],"category_scores_gemma":[0.0005786722,0.0002861566,0.0000866989,0.0008476314,0.0002281156,0.0001745219,0.00003878966,0.0003647058,0.0001588082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000273774,"about_ca_system_score_gemma":0.00009328112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001136421,"about_ca_topic_score_gemma":0.006401729,"domain_scores_codex":[0.9977524,0.0001168548,0.00069867,0.0004227607,0.0003592191,0.0006500593],"domain_scores_gemma":[0.9985019,0.0005803598,0.00006814468,0.0005782662,0.0001126393,0.000158692],"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":[0.0001137933,0.00009877271,0.0003503045,0.00006802733,0.0000185748,0.000008336516,0.0009478783,0.7441798,0.0009388151,0.02680293,0.0000265217,0.2264463],"study_design_scores_gemma":[0.0001330741,0.0002448216,0.0002885131,0.0002134596,0.00001176215,0.000009164648,0.0012673,0.9702102,0.002361227,0.0192314,0.005526056,0.0005030473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6503232,0.0007501958,0.3320099,0.001934343,0.001059182,0.001176939,0.00007149895,0.0009840634,0.01169075],"genre_scores_gemma":[0.9985037,0.00006619768,0.0005251087,0.0002158398,0.0005030897,0.00006536404,0.00001217414,0.00003852354,0.00007003554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3481805,"threshold_uncertainty_score":0.9999591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02643517356787296,"score_gpt":0.2660537146128079,"score_spread":0.2396185410449349,"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."}}