{"id":"W1178556121","doi":"10.1609/aaai.v29i1.9613","title":"Policy Tree: Adaptive Representation for Policy Gradient","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Softmax function; Representation (politics); Computer science; Tree (set theory); Decision tree; Reinforcement learning; Tree structure; Mathematical optimization; Focus (optics); Base (topology); Artificial intelligence; Machine learning; Mathematics; Algorithm; Political science; Binary tree; Law; Artificial neural network","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":[0.0005329148,0.0002151553,0.0002432112,0.0003105931,0.000163136,0.0002606291,0.001933381,0.00008181843,0.000003344009],"category_scores_gemma":[0.002255853,0.0001689464,0.0001370349,0.001209741,0.0002514786,0.0005287059,0.0004050326,0.0001978592,0.00005051513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001985364,"about_ca_system_score_gemma":0.0004949397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002117187,"about_ca_topic_score_gemma":0.000008000897,"domain_scores_codex":[0.9979375,0.00002134819,0.0005401145,0.0004642582,0.0006196169,0.0004171579],"domain_scores_gemma":[0.9975932,0.0001222984,0.0005161914,0.0003750961,0.001227511,0.0001657512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007868306,0.00005049313,0.00007318834,0.0000127452,0.00001449168,1.297429e-7,0.002166224,0.009988277,0.002202344,0.9518257,0.0003654339,0.03322229],"study_design_scores_gemma":[0.00006699236,0.0005729825,0.00008335784,0.00008093109,0.000009473509,0.00000336767,0.0007138132,0.4622943,0.1552108,0.3805704,0.0001985385,0.0001951335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006611168,0.000008470672,0.9412423,0.01792399,0.0005574466,0.00105215,0.000004485068,0.0001552857,0.03244475],"genre_scores_gemma":[0.9847885,0.00001209572,0.01343693,0.000315413,0.0002460002,0.00005962422,9.030217e-7,0.00001468897,0.001125845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9781773,"threshold_uncertainty_score":0.6889436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1818638819922812,"score_gpt":0.3610695971998846,"score_spread":0.1792057152076035,"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."}}