{"id":"W2149418961","doi":"10.1109/adprl.2007.368168","title":"Dual Representations for Dynamic Programming and Reinforcement Learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Bellman equation; Dual (grammatical number); Dynamic programming; Computer science; Mathematical optimization; Divergence (linguistics); Representation (politics); Function (biology); Linear programming; Function approximation; Markov decision process; Exploit; Artificial intelligence; Mathematics; Artificial neural network; Markov process","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":[0.002352016,0.001040432,0.001121822,0.0007981186,0.0004001452,0.002045219,0.001297369,0.001406684,0.004090091],"category_scores_gemma":[0.007195348,0.0005066002,0.0008925165,0.0009951328,0.0016022,0.002871015,0.001953498,0.003304488,0.0006596391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0015751,"about_ca_system_score_gemma":0.001358737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001023799,"about_ca_topic_score_gemma":0.0007747562,"domain_scores_codex":[0.9989225,0.0005202845,0.00005122448,0.0001756215,0.0002295271,0.0001008754],"domain_scores_gemma":[0.9980363,0.001249578,0.000187818,0.0001817376,0.0002436891,0.0001008279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004298906,0.00007375349,0.0003106463,0.0001206027,0.00003030803,0.00004138067,0.0000766341,0.2308168,0.0007232404,0.7306567,0.001392832,0.03571417],"study_design_scores_gemma":[0.00001267139,0.00002970603,0.00003818872,0.00001575026,0.000006982062,0.00002321611,0.00001083542,0.7865827,0.0003627479,0.2107628,0.002147436,0.000006944199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002390286,0.0002209456,0.9945769,0.00023284,0.00004045122,0.00001853628,0.00002399107,0.00003503871,0.002461026],"genre_scores_gemma":[0.4491664,0.001184818,0.538186,0.0003949624,0.0003055838,0.0004937489,0.000216312,0.000145445,0.009906643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004090091,"threshold_uncertainty_score":0.01368272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01736993362014845,"score_gpt":0.3033845091280638,"score_spread":0.2860145755079154,"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."}}