{"id":"W2162664081","doi":"","title":"Dual Temporal Difference Learning","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Dual (grammatical number); Convergence (economics); Temporal difference learning; Reinforcement learning; Computer science; Artificial intelligence; Dynamic programming; Basis (linear algebra); Machine learning; Algorithm; Mathematical optimization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002532941,0.000556622,0.000754662,0.0004732975,0.000330164,0.001089163,0.001393145,0.001006819,0.004466209],"category_scores_gemma":[0.01089214,0.0003056839,0.0004427002,0.0004944818,0.001557584,0.002564791,0.002106066,0.002067786,0.0004289778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001037061,"about_ca_system_score_gemma":0.0009954362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007930725,"about_ca_topic_score_gemma":0.000645476,"domain_scores_codex":[0.9989383,0.0004374724,0.00005295685,0.0002170953,0.0002623424,0.0000918605],"domain_scores_gemma":[0.9969438,0.001717603,0.0002492593,0.0003543285,0.0005283028,0.000206766],"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":[0.0004016224,0.0002350913,0.001496205,0.000182931,0.00007764975,0.00007739572,0.0001639153,0.2884901,0.004878539,0.5337355,0.002237102,0.168024],"study_design_scores_gemma":[0.00002613954,0.00007115005,0.00008191165,0.00001105903,0.000008061853,0.0000275907,0.000009547556,0.8884637,0.001123647,0.1091261,0.001043441,0.000007655803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01883047,0.0001957369,0.976554,0.0003606449,0.00007434786,0.00003751309,0.00004016849,0.0001179991,0.003789084],"genre_scores_gemma":[0.7987632,0.0002803151,0.1944079,0.0003132662,0.00006950675,0.0001697914,0.0001255554,0.00006339196,0.005807111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004466209,"threshold_uncertainty_score":0.01494092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01651114802915592,"score_gpt":0.2444750998830643,"score_spread":0.2279639518539084,"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."}}