{"id":"W2027648864","doi":"10.2991/agi.2010.22","title":"GQ( ): A general gradient algorithm for temporal-difference prediction learning with eligibility traces","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Algorithm; Temporal difference learning; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002528707,0.0009073819,0.001113972,0.0007093922,0.0003973754,0.001030508,0.002518483,0.001841132,0.005423053],"category_scores_gemma":[0.006968262,0.0005336033,0.0006177147,0.0007473155,0.0010506,0.002075286,0.002155966,0.002113338,0.001083969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133074,"about_ca_system_score_gemma":0.002120252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006174657,"about_ca_topic_score_gemma":0.004676297,"domain_scores_codex":[0.9993852,0.0002094904,0.00004412916,0.0001325429,0.000159303,0.00006938798],"domain_scores_gemma":[0.9988129,0.0006701143,0.00008467666,0.0001163748,0.0002341908,0.00008171437],"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":[0.0002490602,0.0001443331,0.0009947249,0.0001789367,0.00007416377,0.00009073278,0.000134179,0.5094894,0.00242225,0.09726028,0.006282497,0.3826795],"study_design_scores_gemma":[0.00003217225,0.00003008253,0.00005238993,0.000008854149,0.000005418294,0.00001807645,0.000005313682,0.9791911,0.000436153,0.01904161,0.001172414,0.00000637876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002011071,0.00007381991,0.9966607,0.0001070157,0.00003303821,0.00004822846,0.00002681276,0.0004789899,0.0005603284],"genre_scores_gemma":[0.1549502,0.0001780422,0.8397954,0.0003457774,0.00006955458,0.0004276026,0.0002111724,0.0003973737,0.003624978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006174657,"threshold_uncertainty_score":0.01814187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01308984256616065,"score_gpt":0.2579115051959552,"score_spread":0.2448216626297946,"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."}}