{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001384177,0.0008674485,0.001608727,0.0006156737,0.0004519626,0.0009069126,0.00117281,0.001135149,0.001952464],"category_scores_gemma":[0.004142447,0.0006122989,0.0008120968,0.0006928028,0.0008196833,0.001273473,0.001300406,0.001670664,0.0004376255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009315041,"about_ca_system_score_gemma":0.002041031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007478093,"about_ca_topic_score_gemma":0.004356426,"domain_scores_codex":[0.9989479,0.0003157601,0.0000670562,0.000184345,0.000360532,0.0001243801],"domain_scores_gemma":[0.998551,0.0007785615,0.0001284476,0.0001355822,0.0003238175,0.0000827261],"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":[0.00009134349,0.00004820773,0.000441197,0.00007188688,0.00002836625,0.0000430518,0.00007172691,0.9356131,0.001478997,0.01395842,0.0006852082,0.0474685],"study_design_scores_gemma":[0.000004664442,0.000008265047,0.0000139684,0.000001474798,0.000001293727,0.000002901327,0.000001553346,0.9985885,0.0001236012,0.001163337,0.00008895581,0.000001465778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006782828,0.0001169795,0.9920267,0.00004825805,0.0000182103,0.00002992418,0.00001928075,0.0002449503,0.0007127413],"genre_scores_gemma":[0.5534014,0.0002322468,0.4430731,0.0001801183,0.00003924307,0.0004356547,0.0002409909,0.0001340397,0.002263198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007478093,"threshold_uncertainty_score":0.01486909,"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."}}