{"id":"W3011813374","doi":"10.1109/cdc40024.2019.9029898","title":"Approximate information state for partially observed systems","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Observable; Computer science; State (computer science); Reinforcement learning; Partially observable Markov decision process; Markov decision process; Benchmark (surveying); Markov process; Mathematical optimization; Constructive; Artificial intelligence; Theoretical computer science; Markov chain; Markov model; Machine learning; Mathematics; Algorithm","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":[0.001705,0.0008805416,0.001051241,0.0008982979,0.0003960015,0.001391801,0.001138434,0.001090267,0.002594992],"category_scores_gemma":[0.009307353,0.0005437015,0.0009281138,0.0007847968,0.001880716,0.003196672,0.001380052,0.002155079,0.0002782718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001776459,"about_ca_system_score_gemma":0.001581017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004035936,"about_ca_topic_score_gemma":0.002920592,"domain_scores_codex":[0.9986168,0.0005250127,0.00006866292,0.0002630081,0.0004000375,0.0001264628],"domain_scores_gemma":[0.9948991,0.003717721,0.000549081,0.0003428223,0.0003709762,0.0001202265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006279682,0.00002982918,0.0004671192,0.00008410142,0.000020834,0.0000499593,0.00008896853,0.894354,0.0006568257,0.09212135,0.0003943565,0.01166979],"study_design_scores_gemma":[0.000004665426,0.00001489291,0.00006801073,0.000008631409,0.000003416327,0.000006375829,0.000006981187,0.9650055,0.0003024644,0.03427285,0.0003018187,0.000004511436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0130435,0.0001411343,0.984928,0.000148616,0.0000100794,0.00003299567,0.0001250232,0.0002260423,0.001344627],"genre_scores_gemma":[0.7709622,0.0004493619,0.2251135,0.0001026223,0.00004177146,0.0003645692,0.0006670876,0.0001423914,0.002156527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004035936,"threshold_uncertainty_score":0.01288915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02619214429429857,"score_gpt":0.2265800874326913,"score_spread":0.2003879431383928,"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."}}