{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002566319,0.001327205,0.001929555,0.0007525482,0.0006377326,0.001096889,0.001627268,0.001466684,0.002671133],"category_scores_gemma":[0.008507795,0.0009025868,0.0009381459,0.000587251,0.002456486,0.0015113,0.002293265,0.002539185,0.0003749053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001437738,"about_ca_system_score_gemma":0.002696638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006249717,"about_ca_topic_score_gemma":0.006193099,"domain_scores_codex":[0.9986124,0.0006090953,0.00006899555,0.0002365497,0.0003015625,0.0001713137],"domain_scores_gemma":[0.9937394,0.005213795,0.0003391207,0.000236157,0.0002637393,0.0002078285],"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":[0.00007229197,0.00004368364,0.0002622482,0.00006525712,0.00002879363,0.00005746813,0.00007896466,0.9718622,0.0003040597,0.01444878,0.0004790098,0.01229725],"study_design_scores_gemma":[0.00001774559,0.00002427261,0.00002504927,0.000007597071,0.000004788069,0.000007113746,0.000006671844,0.9907691,0.0001564902,0.008788875,0.0001880479,0.000004335907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02234294,0.0003063784,0.9715505,0.0002904749,0.00003585089,0.00008776288,0.00004645546,0.0007456403,0.004594066],"genre_scores_gemma":[0.7943087,0.0002562776,0.2014967,0.0002385123,0.00003955951,0.0004917534,0.0001313689,0.000200474,0.002836615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006249717,"threshold_uncertainty_score":0.01357216,"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."}}