{"id":"W7124153011","doi":"10.65109/actd7997","title":"Escaping local optima in POMDP planning as inference","year":2011,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Partially observable Markov decision process; Inference; Reinforcement learning; Controller (irrigation); Greedy algorithm; Local planning; Control (management)","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":[0.003185968,0.0009618637,0.001756514,0.0006389274,0.0006255592,0.0009517201,0.001617668,0.001333022,0.001370095],"category_scores_gemma":[0.009139358,0.000849132,0.000789176,0.0006360751,0.002637364,0.001780458,0.002316017,0.00256275,0.0002264488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001389996,"about_ca_system_score_gemma":0.00155363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006000745,"about_ca_topic_score_gemma":0.005734394,"domain_scores_codex":[0.9989049,0.0004730506,0.00005612054,0.0001795736,0.0002518047,0.0001345311],"domain_scores_gemma":[0.9954372,0.003593947,0.0003009536,0.0003108865,0.0002124893,0.0001445002],"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":[0.00004852721,0.00001968005,0.0002655095,0.00004067109,0.00002524045,0.00003833038,0.00007317133,0.9685348,0.0004655051,0.0176649,0.0002114683,0.01261215],"study_design_scores_gemma":[0.0000135429,0.00001578524,0.00002803565,0.00000635648,0.000005923586,0.000005003868,0.000007301292,0.985077,0.00026096,0.01445834,0.0001176035,0.000004216935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02240967,0.0002714114,0.9745972,0.0002846201,0.00002031303,0.00004538508,0.00002322234,0.0004485169,0.001899736],"genre_scores_gemma":[0.7535508,0.0002399269,0.244038,0.0002012929,0.00003127314,0.0002101493,0.00005495865,0.0001253519,0.001548217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006000745,"threshold_uncertainty_score":0.01684922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08219326181887587,"score_gpt":0.305530048721098,"score_spread":0.2233367869022221,"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."}}