{"id":"W2153516274","doi":"10.5555/2772879.2773311","title":"Incremental Policy Iteration with Guaranteed Escape from Local Optima in POMDP Planning","year":2015,"lang":"en","type":"article","venue":"Kent Academic Repository (University of Kent)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Partially observable Markov decision process; Mathematical optimization; Markov decision process; Local optimum; Bounded function; Controller (irrigation); Local search (optimization); State (computer science); Markov chain; Markov process; Artificial intelligence; Markov model; Algorithm; Mathematics; Machine learning","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":[0.0002540026,0.0001657101,0.0002285544,0.0002707051,0.0001319015,0.00004919844,0.0009604542,0.0001663178,0.000005499678],"category_scores_gemma":[0.00001946257,0.0001874911,0.00004942969,0.0004194865,0.0001394222,0.0009912037,0.0003073625,0.0004524757,0.00001630756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005038314,"about_ca_system_score_gemma":0.0002587375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001276787,"about_ca_topic_score_gemma":0.000008401803,"domain_scores_codex":[0.9983536,0.0001256416,0.000265118,0.0003773473,0.0006018508,0.000276449],"domain_scores_gemma":[0.9990684,0.00005334439,0.0003069815,0.0003402776,0.00008017774,0.0001508269],"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":[0.000269058,0.00005524278,0.1633542,0.00002162197,0.00007560067,0.0002504766,0.0178347,0.8083981,0.005856699,0.001488179,0.001564267,0.0008317937],"study_design_scores_gemma":[0.003412481,0.0004489536,0.04404292,0.0004166347,0.00003553893,0.00006398937,0.005528101,0.9411195,0.003110378,0.0001411208,0.001238322,0.0004420684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5112414,0.00009686719,0.4854248,0.0003034094,0.0001480769,0.0001603887,0.000001070359,0.00007555215,0.002548419],"genre_scores_gemma":[0.9871295,0.000009985622,0.01221839,0.00009016383,0.00007683667,3.792414e-7,0.00001252215,0.000008786315,0.0004534384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4758881,"threshold_uncertainty_score":0.7645664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01951838118523338,"score_gpt":0.2283262394246332,"score_spread":0.2088078582393998,"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."}}