{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004505109,0.0001826239,0.00017067,0.00007936605,0.0002634327,0.000246102,0.0005579583,0.000086987,0.00001960147],"category_scores_gemma":[0.00007276851,0.0001352367,0.00006044418,0.0002168156,0.00007928703,0.0003920875,0.0001034573,0.0003940005,0.00001030021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003209908,"about_ca_system_score_gemma":0.00007800527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007327184,"about_ca_topic_score_gemma":0.00003708509,"domain_scores_codex":[0.9984556,0.00004132954,0.0002747715,0.0005122874,0.0003545904,0.0003614297],"domain_scores_gemma":[0.9989601,0.0001071669,0.0001454339,0.0004938797,0.0001677224,0.0001257483],"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":[0.00005295107,0.0003826831,0.1630436,0.00009862524,0.0001323855,0.00001023708,0.002571864,0.4418991,0.008004176,0.03400784,0.001271263,0.3485253],"study_design_scores_gemma":[0.0004507315,0.0006919646,0.01398781,0.000008676298,0.000008208644,0.00001448373,0.0000243212,0.9795952,0.001496789,0.0002739739,0.003266527,0.0001813111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1315181,0.000004918113,0.8664453,0.0001775486,0.0004156128,0.0003806311,0.000001546308,0.0003561436,0.0007002243],"genre_scores_gemma":[0.4479979,0.000003115518,0.5469892,0.00005634071,0.0001122827,0.00005511564,0.00001292325,0.00001063015,0.004762543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5376961,"threshold_uncertainty_score":0.551479,"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."}}