{"id":"W1872977731","doi":"10.1609/icaps.v23i1.13579","title":"Linear Fitted-Q Iteration with Multiple Reward Functions","year":2013,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Triangulation; Computer science; Mathematical optimization; Function (biology); Markov decision process; Construct (python library); Field (mathematics); Bellman equation; Reduction (mathematics); Algorithm; Mathematics; Artificial intelligence; Statistics; Markov process; Geometry","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":[0.001392473,0.0001284914,0.0002830765,0.0001849483,0.000185123,0.0001945252,0.0002475224,0.00007956833,0.0001301601],"category_scores_gemma":[0.00124203,0.0001113011,0.0000391628,0.000112472,0.00005443913,0.0004848775,0.00004634193,0.0001832423,0.0001394086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008041265,"about_ca_system_score_gemma":0.00004095583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001932254,"about_ca_topic_score_gemma":0.000003451035,"domain_scores_codex":[0.9984068,0.00001358547,0.001003195,0.0002895754,0.0001285829,0.0001582933],"domain_scores_gemma":[0.998333,0.0001900738,0.001006307,0.00008867698,0.0003171947,0.00006473391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001112209,0.0001421833,0.8363718,0.0003109379,0.0003007858,4.323265e-7,0.004708079,0.008003264,0.002713115,0.1319745,0.01517575,0.0001879001],"study_design_scores_gemma":[0.0005766453,0.00008979504,0.05994361,0.0006649623,0.00000678124,0.00001082853,0.00211664,0.9321973,0.0003262094,0.003140106,0.0007213695,0.0002057557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725165,0.00006518036,0.0005407047,0.01864858,0.0002680099,0.0002973076,0.00004834433,0.0001468392,0.007468565],"genre_scores_gemma":[0.9927787,0.00000646939,0.005211,0.001267185,0.0001019618,0.00005542111,0.0000156518,0.00001381023,0.0005498266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.924194,"threshold_uncertainty_score":0.4538729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2188434596026902,"score_gpt":0.3750649152408874,"score_spread":0.1562214556381972,"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."}}