{"id":"W1987974668","doi":"10.1145/1143844.1143861","title":"Learning predictive state representations using non-blind policies","year":2006,"lang":"en","type":"article","venue":"","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; State (computer science); Artificial intelligence; Machine learning; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00004827066,0.00007525491,0.00008622132,0.00009235497,0.000088835,0.00004978722,0.00003554522,0.00002951808,0.00004584843],"category_scores_gemma":[0.000007565131,0.00007355244,0.00003538045,0.0001637879,0.00001329788,0.0001090802,0.000007456598,0.00009499631,0.00003673917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004633462,"about_ca_system_score_gemma":0.000006931741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002113409,"about_ca_topic_score_gemma":0.0001796724,"domain_scores_codex":[0.999502,0.00001617663,0.0001558599,0.00008543253,0.00009170812,0.0001488134],"domain_scores_gemma":[0.9998213,0.00002351059,0.0000189018,0.00007964453,0.00002775333,0.00002890267],"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":[0.000006003931,0.000004377027,0.001830644,0.000006653253,0.00002047538,0.000001210311,0.0002826965,0.9732461,0.02386064,0.00004754458,0.0004156388,0.0002780147],"study_design_scores_gemma":[0.0004257497,0.00001744059,0.004534303,0.000007712066,0.00000747897,0.000006579875,0.000689353,0.9870127,0.005016884,0.00008213316,0.002104046,0.00009556382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8094898,0.00004402774,0.09668856,0.00002129116,0.0002855072,0.0001607361,0.000003985566,0.0004695103,0.09283651],"genre_scores_gemma":[0.9951647,0.000003043754,0.0001525666,0.00000836432,0.0001409898,0.00001317018,0.000003295215,0.00001766317,0.004496215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1856748,"threshold_uncertainty_score":0.3194857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00933989075119607,"score_gpt":0.2474497616653368,"score_spread":0.2381098709141407,"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."}}