{"id":"W2115083386","doi":"10.1007/978-3-642-04174-7_43","title":"Learning the Difference between Partially Observable Dynamical Systems","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Observable; Computer science; Markov decision process; Divergence (linguistics); Reinforcement learning; Dynamical systems theory; Key (lock); Temporal difference learning; Markov process; Markov chain; Artificial intelligence; Process (computing); Mathematical optimization; Machine learning; Mathematics; Statistics","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":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001544209,0.0006778379,0.0007371702,0.0004261674,0.0006857551,0.001805739,0.006637461,0.0004276863,0.000007994659],"category_scores_gemma":[0.00025739,0.0004991395,0.0001662521,0.000709231,0.0007507924,0.0004879945,0.001767581,0.002319125,0.00008773235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004110905,"about_ca_system_score_gemma":0.0005561899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004772624,"about_ca_topic_score_gemma":0.00002015631,"domain_scores_codex":[0.9946228,0.0001462287,0.0008253494,0.001522391,0.001804311,0.001078892],"domain_scores_gemma":[0.9957723,0.001323751,0.0005482085,0.001873513,0.000261457,0.000220764],"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":[0.000001458493,0.000005022452,0.0006869675,0.00002012132,0.0000112456,0.00002670831,0.0002929535,0.7779467,0.00002310936,0.009256474,0.000004698606,0.2117245],"study_design_scores_gemma":[0.0001497662,0.0003332597,0.002387528,0.0004222772,0.00001603884,0.0000294615,2.518262e-7,0.982404,0.00006466273,0.01142596,0.002146465,0.0006203508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001415059,0.0002265295,0.9934875,0.0009140753,0.001452988,0.0005261107,0.000001179326,0.0003156711,0.002934418],"genre_scores_gemma":[0.8423743,0.0001010046,0.1461943,0.001266925,0.001513144,0.00002069133,0.00001940544,0.00008553213,0.008424706],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8472932,"threshold_uncertainty_score":0.9999825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02598432659031535,"score_gpt":0.244464198501162,"score_spread":0.2184798719108467,"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."}}