{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003501612,0.00009079047,0.0001173603,0.00005545865,0.00004948695,0.0004619306,0.0005064695,0.00003290782,0.000008524074],"category_scores_gemma":[0.00002974699,0.00007651403,0.00004003913,0.0001264868,0.00000695011,0.001758929,0.0001178881,0.00005026774,0.0005093636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000308784,"about_ca_system_score_gemma":0.00004634363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001654487,"about_ca_topic_score_gemma":6.463339e-7,"domain_scores_codex":[0.9990677,0.00002024899,0.0003071223,0.0001263584,0.0002284321,0.0002501486],"domain_scores_gemma":[0.9991776,0.00006782725,0.0001480785,0.0004259609,0.0001312022,0.00004928383],"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":[0.000004183437,0.000003454726,0.0006172283,0.00009963996,0.00001056717,1.071146e-7,0.0002938326,0.9116805,0.00009245772,0.0853408,0.0009143801,0.0009428515],"study_design_scores_gemma":[0.0003703028,0.00009683673,0.0002899302,0.00001242301,0.000001661899,0.000001067319,0.00002757641,0.9782787,0.0004524161,0.0001462673,0.02020847,0.0001143395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003188762,0.000005164659,0.9888303,0.0001261363,0.0008046383,0.0007514332,0.000001103138,0.0002688716,0.006023575],"genre_scores_gemma":[0.881992,0.000005719714,0.106039,0.0005171783,0.00003698633,0.000102181,0.00003368494,0.000012309,0.01126091],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8827913,"threshold_uncertainty_score":0.6547008,"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."}}