{"id":"W2141690016","doi":"10.1145/1553374.1553383","title":"Predictive representations for policy gradient in POMDPs","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Artificial intelligence; Mathematical optimization; 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":[0.0001175709,0.00006357427,0.00007152678,0.000191536,0.00005295794,0.00006625759,0.000375808,0.00002588645,0.000002747342],"category_scores_gemma":[0.0001250488,0.00005908623,0.00003598773,0.0004139658,0.00001134257,0.0002963179,0.00005057353,0.00005804218,0.00001261972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009488997,"about_ca_system_score_gemma":0.00007202783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004433954,"about_ca_topic_score_gemma":0.000004151888,"domain_scores_codex":[0.9992646,0.00001865419,0.000167418,0.0002020624,0.0001337284,0.0002135198],"domain_scores_gemma":[0.9994634,0.00008116577,0.00004248822,0.0003176954,0.00004629157,0.00004895872],"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":[0.000003149436,0.00003925431,0.0006984597,0.000001894502,0.000004637631,0.000001448118,0.001007581,0.3349949,0.00003886255,0.6593247,0.001397888,0.002487179],"study_design_scores_gemma":[0.0004157851,0.000294968,0.02665138,0.000006477802,0.000001850707,0.000002682691,0.00003496479,0.9517042,0.0002760719,0.01864497,0.001875567,0.0000910574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005351647,0.000004847596,0.9637555,0.006090499,0.00008065532,0.0003048858,4.092985e-7,0.0001692726,0.02905869],"genre_scores_gemma":[0.8462747,0.0000064485,0.1503645,0.0009290345,0.00006565108,0.00002454654,0.000003101507,0.000003390592,0.002328554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8457395,"threshold_uncertainty_score":0.2409467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02090219095413405,"score_gpt":0.3127686912663465,"score_spread":0.2918665003122125,"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."}}