{"id":"W2086608109","doi":"10.1109/tnn.2011.2168422","title":"Hierarchical Approximate Policy Iteration With Binary-Tree State Space Decomposition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Markov decision process; Reinforcement learning; Kernel (algebra); State space; Mathematical optimization; Tree (set theory); Algorithm; Markov process; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001136083,0.0002494207,0.0001732218,0.0002620808,0.0003313938,0.0001903529,0.0004452183,0.00008762538,0.00002012242],"category_scores_gemma":[0.000001549261,0.0002144571,0.00008181635,0.0006867955,0.00008787551,0.000758876,0.000005866645,0.0005506611,0.00002233867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007982281,"about_ca_system_score_gemma":0.00003915852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004706746,"about_ca_topic_score_gemma":0.00002393523,"domain_scores_codex":[0.9984064,0.0001340119,0.0002711058,0.0004195757,0.0003097228,0.0004592411],"domain_scores_gemma":[0.9990567,0.00007790827,0.0001154098,0.000517436,0.00006817144,0.0001643648],"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":[0.0001199623,0.0000817185,0.00002619478,0.000006725684,0.00002457812,0.00002421692,0.0005121208,0.9800164,0.0001623518,0.001117937,0.00003371427,0.01787414],"study_design_scores_gemma":[0.0004470703,0.0008184926,0.0004585186,0.00003313038,0.00001397423,0.00005217161,0.000005336851,0.995848,0.001889491,0.0001545323,0.00003334471,0.0002459612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01130733,0.000006770178,0.9861984,0.0005980782,0.0004364973,0.0002980149,0.000001564308,0.0003744664,0.0007788641],"genre_scores_gemma":[0.9660975,0.00002606609,0.03292823,0.0003958311,0.00007619476,0.00003529065,0.000004774608,0.00002696964,0.0004091834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9547901,"threshold_uncertainty_score":0.8745309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01815426389084072,"score_gpt":0.2456372989205274,"score_spread":0.2274830350296866,"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."}}