{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000438578,0.0002939538,0.0002492985,0.0005202671,0.0002189153,0.0003912879,0.000911106,0.0001116512,0.0002661272],"category_scores_gemma":[0.0005468033,0.0003073795,0.0001063157,0.0002961423,0.00003431998,0.0008108103,0.0001379966,0.0007696535,0.00009174106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002577042,"about_ca_system_score_gemma":0.00006896994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004275498,"about_ca_topic_score_gemma":0.00000992181,"domain_scores_codex":[0.9976214,0.000149161,0.0005450438,0.0005547928,0.0007178633,0.0004117136],"domain_scores_gemma":[0.9987054,0.0002293574,0.0003478339,0.0002801006,0.0003419766,0.00009530284],"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":[0.00002388758,0.0000402911,0.0007095393,0.0000086507,0.00001967703,0.000004901631,0.0006396675,0.9488567,0.0002906632,0.01577782,0.00004980162,0.03357848],"study_design_scores_gemma":[0.001297845,0.0003495623,0.0001110787,0.00009177523,0.000004354752,0.000001369399,0.00004047594,0.9944002,0.0003158694,0.0007590117,0.002307345,0.0003211006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005714335,0.00001472754,0.987839,0.002149628,0.0003596194,0.000363702,0.000002186419,0.0005254503,0.008174283],"genre_scores_gemma":[0.9196168,0.00004237641,0.07337959,0.0003114474,0.00007037633,0.0001160488,0.000169501,0.00003005661,0.006263813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9190453,"threshold_uncertainty_score":0.9999378,"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."}}