{"id":"W4200372371","doi":"10.1002/cpe.6743","title":"Scalable grid‐based approximation algorithms for partially observable Markov decision processes","year":2021,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Computer science; Markov decision process; Scalability; Observable; Mathematical optimization; Implementation; Grid; Markov process; Process (computing); Focus (optics); Algorithm; Markov chain; Markov model; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003250491,0.0001357452,0.0001474628,0.00004499668,0.0003781519,0.0006024577,0.0001798099,0.00005655095,0.000006658689],"category_scores_gemma":[0.001678907,0.0001358119,0.00002141405,0.000410182,0.00006368129,0.002359442,0.0001120241,0.00009448268,0.000003805249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001571822,"about_ca_system_score_gemma":0.0002794247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005264318,"about_ca_topic_score_gemma":0.000001136805,"domain_scores_codex":[0.9986756,0.00007455219,0.0003043898,0.0004577896,0.0002734095,0.0002142489],"domain_scores_gemma":[0.9975835,0.001263039,0.0002133268,0.0001810764,0.0006672707,0.00009179339],"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":[0.0001352684,0.0002785682,0.001204442,0.0007223407,0.00003778428,0.0000301915,0.01195609,0.2295646,0.0005983859,0.01707579,0.001282313,0.7371142],"study_design_scores_gemma":[0.0006343959,0.0001483949,0.0002241676,0.00008728109,0.00001526248,0.00003166003,0.0007981002,0.9807013,0.002100269,0.0009266083,0.01413611,0.0001964511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005458253,0.001055121,0.9915822,0.0008321505,0.0004602975,0.0002353655,0.000001876978,0.00007701764,0.0002976732],"genre_scores_gemma":[0.4112166,0.0003708728,0.5871826,0.0008865413,0.00007063757,0.0001275946,0.00004119769,0.000009041389,0.00009482712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7511367,"threshold_uncertainty_score":0.5809514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04756454524991755,"score_gpt":0.3385360643285482,"score_spread":0.2909715190786307,"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."}}