{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006521672,0.00009835653,0.00008967092,0.0001129528,0.0002645074,0.0002022623,0.0001931864,0.0000392725,0.000009304144],"category_scores_gemma":[0.0001353492,0.00009390506,0.00003684328,0.000198237,0.00003595963,0.0003517561,0.0001865789,0.0001152662,0.000008880188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004070095,"about_ca_system_score_gemma":0.00002262319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001341424,"about_ca_topic_score_gemma":0.000007012721,"domain_scores_codex":[0.9988951,0.00001356377,0.0002684213,0.0002647016,0.0002118613,0.0003463146],"domain_scores_gemma":[0.9992504,0.0002427263,0.00009736021,0.0002401554,0.00008317241,0.00008624316],"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":[0.00001090123,0.00001407267,0.003500995,0.00003769438,0.00003528946,0.000007386043,0.001548708,0.7898555,0.0004496053,0.1134475,0.0001820252,0.09091039],"study_design_scores_gemma":[0.0003986477,0.0002124738,0.002157075,0.00001012571,0.000006922416,0.00001409621,0.0003628605,0.9838849,0.0003406441,0.000174577,0.01228304,0.0001546003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001823563,0.00001582973,0.9918555,0.0003333669,0.0001588539,0.0003997169,3.951091e-8,0.0002516226,0.005161479],"genre_scores_gemma":[0.674433,0.000006436754,0.3158379,0.00008958503,0.00002428666,0.00002037652,0.000007180602,0.000008287421,0.00957293],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6760176,"threshold_uncertainty_score":0.3829337,"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."}}