{"id":"W2295665692","doi":"10.5555/2034396.2034406","title":"Efficient planning in R-max","year":2011,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Mathematical optimization; Markov decision process; Value (mathematics); Artificial intelligence; Algorithm; Machine learning; Mathematics; Markov process","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":[0.000422518,0.0002346339,0.0002696829,0.0002077403,0.0001380108,0.000114042,0.0005529722,0.00008858023,0.00001162173],"category_scores_gemma":[0.00003259089,0.0002087858,0.00004602688,0.0002605201,0.00005130504,0.0001791261,0.0003597204,0.0001831429,0.00009271448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007863747,"about_ca_system_score_gemma":0.00002743268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005488077,"about_ca_topic_score_gemma":0.000003993842,"domain_scores_codex":[0.9981008,0.0001423727,0.0004327447,0.000508761,0.0003472177,0.0004681678],"domain_scores_gemma":[0.9991097,0.00004626529,0.0002006228,0.0004206666,0.00006413563,0.0001586307],"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":[0.0000303231,0.0003485225,0.09871728,0.00008848376,0.0001419465,0.0004054215,0.02814539,0.8585681,0.0001266363,0.01105008,0.0006090404,0.001768763],"study_design_scores_gemma":[0.0008460768,0.0001054863,0.0825232,0.0001589551,0.000006765047,0.00001216061,0.0006013604,0.9145647,0.00003155422,0.000005588693,0.0009060698,0.0002381151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1227022,0.0004130622,0.8687607,0.00001131772,0.001201179,0.0006809322,0.000002480599,0.0001216693,0.006106424],"genre_scores_gemma":[0.9890969,0.00001631232,0.009579816,0.00009156671,0.00002860669,0.00003332719,0.000001919376,0.00001770074,0.001133824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8663947,"threshold_uncertainty_score":0.8514036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1242030640907431,"score_gpt":0.2922210493630056,"score_spread":0.1680179852722625,"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."}}