{"id":"W183139520","doi":"","title":"Stochastic local search for POMDP controllers","year":2004,"lang":"en","type":"article","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Partially observable Markov decision process; Heuristics; Computer science; Markov decision process; Mathematical optimization; Dynamic programming; Observable; Controller (irrigation); State (computer science); Markov process; Markov chain; Mathematics; Algorithm; Machine learning; Markov model","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":[0.0002347677,0.000104721,0.0001330602,0.00006911819,0.0001198869,0.0001012068,0.0005549854,0.00004732991,0.00001193317],"category_scores_gemma":[0.00005680722,0.00009897384,0.00006198263,0.0001763692,0.00006620698,0.0001362923,0.0001198205,0.0001258261,0.0001482668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001188055,"about_ca_system_score_gemma":0.0001447927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004704953,"about_ca_topic_score_gemma":0.000002361132,"domain_scores_codex":[0.9989797,0.00001851361,0.0001223555,0.0002345541,0.0002753301,0.0003695709],"domain_scores_gemma":[0.9992592,0.000143229,0.00004092248,0.0003710205,0.00008291184,0.0001027011],"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":[0.00001184838,0.000009280388,0.000005415369,0.000007093986,0.00001158629,0.000002647425,0.001132705,0.9380767,0.0001396696,0.05930942,0.0001575064,0.001136121],"study_design_scores_gemma":[0.002178352,0.0003018056,0.00007258166,0.00002186659,0.000006610235,0.000007979172,0.0003274727,0.9941766,0.0008928931,0.0007444065,0.001094403,0.0001750749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001159272,0.00003183345,0.9931116,0.0032193,0.0002346172,0.0003364542,2.58962e-7,0.0001575403,0.00174917],"genre_scores_gemma":[0.9501579,0.000001199384,0.04703486,0.0002896271,0.00005775004,0.00001941997,0.000001465691,0.00001198912,0.002425836],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489986,"threshold_uncertainty_score":0.4036036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02851222499342767,"score_gpt":0.3227567584077197,"score_spread":0.294244533414292,"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."}}