{"id":"W1498235675","doi":"","title":"AEMS: an anytime online search algorithm for approximate policy refinement in large POMDPs","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Partially observable Markov decision process; Markov decision process; Computation; Task (project management); Mathematical optimization; State space; State (computer science); Function (biology); Bellman equation; Online algorithm; Observable; Algorithm; Markov process; Markov chain; Machine learning; Markov model; 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":[0.00180929,0.0001778065,0.0001951366,0.0004568327,0.0001107095,0.0001352789,0.0009376105,0.00008546744,0.00003121377],"category_scores_gemma":[0.00005008391,0.0001629399,0.00005617113,0.0007185733,0.00002211692,0.0004374674,0.0003789035,0.0001997502,0.00003498107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002104263,"about_ca_system_score_gemma":0.0001540545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002481839,"about_ca_topic_score_gemma":0.00009951265,"domain_scores_codex":[0.9977039,0.0000454184,0.0004493373,0.0004451109,0.0004505794,0.0009056586],"domain_scores_gemma":[0.9988682,0.00009168863,0.0000614757,0.000673347,0.0001233142,0.000182017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003970433,0.002198609,0.002627472,0.0001366866,0.00008061356,0.00007228323,0.004720513,0.1486233,0.001069563,0.3373325,0.0008593947,0.5022393],"study_design_scores_gemma":[0.001039745,0.000342951,0.002065602,0.00001195147,0.000002093016,0.000005352184,0.0001310065,0.9894003,0.0007526678,0.0001997902,0.00584176,0.0002068046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00377123,0.00001233202,0.9918442,0.0007854183,0.0001129319,0.0004971733,0.000006687127,0.0002932408,0.002676827],"genre_scores_gemma":[0.02813558,0.00001226089,0.9673994,0.001086038,0.0002387791,0.00001447786,0.00005650365,0.00002358066,0.003033352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.840777,"threshold_uncertainty_score":0.6644498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03203246700207627,"score_gpt":0.3428225774256188,"score_spread":0.3107901104235425,"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."}}