{"id":"W18175453","doi":"10.1525/tph.2007.29.3.87","title":"Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs","year":2002,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Oracle; Computer science; Planner; Mathematical optimization; Linear programming; Artificial intelligence; Machine learning; Algorithm; 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":[0.003189532,0.001335515,0.002167901,0.0007845939,0.0005857314,0.001029301,0.001592689,0.001717149,0.004118219],"category_scores_gemma":[0.009815553,0.0008343204,0.0007095321,0.0005760841,0.001607974,0.001364203,0.002034388,0.001959056,0.0003698321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001545161,"about_ca_system_score_gemma":0.001937701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056829,"about_ca_topic_score_gemma":0.00884378,"domain_scores_codex":[0.9992098,0.0004189174,0.00004491651,0.0001063351,0.00009843826,0.0001216881],"domain_scores_gemma":[0.9931942,0.005773584,0.0003146614,0.0001751438,0.0003289902,0.0002133541],"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":[0.0000579886,0.00002475377,0.0002975464,0.00004055703,0.0000222092,0.00002620405,0.00003688104,0.9854154,0.00008188817,0.006296261,0.0003026883,0.007397663],"study_design_scores_gemma":[0.00001792578,0.00001721551,0.00001579844,0.000004730849,0.00000277018,0.000002609192,0.00000365472,0.9958584,0.00003254777,0.0039506,0.00009172709,0.000002031326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04503132,0.0004660931,0.9492612,0.0005132784,0.00006238707,0.0001232622,0.00007966167,0.0005550835,0.003907708],"genre_scores_gemma":[0.8914745,0.0002160717,0.1043474,0.0001869756,0.00004577282,0.000489363,0.0001459462,0.0001041142,0.002989718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01056829,"threshold_uncertainty_score":0.02101356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08004596865886063,"score_gpt":0.3027935798906811,"score_spread":0.2227476112318204,"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."}}