{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004440727,0.001141856,0.00151523,0.0007608965,0.0006687648,0.001211709,0.002325661,0.001963597,0.009488648],"category_scores_gemma":[0.01718115,0.0008968971,0.001164648,0.0007782021,0.001625979,0.001718535,0.002245581,0.002495904,0.001618013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001943492,"about_ca_system_score_gemma":0.00333839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008154825,"about_ca_topic_score_gemma":0.00756196,"domain_scores_codex":[0.998329,0.0007643506,0.0001089607,0.0002498881,0.0003408526,0.0002068769],"domain_scores_gemma":[0.9934015,0.005022779,0.0003207705,0.0003177623,0.0007152898,0.0002218982],"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":[0.00013772,0.0000653892,0.0005372522,0.0001089631,0.0000367139,0.00009513203,0.0001326974,0.8966503,0.0006357373,0.0472204,0.001122033,0.0532577],"study_design_scores_gemma":[0.00001716287,0.0000229478,0.00002394039,0.00001160149,0.00000352415,0.00001075502,0.000008213703,0.9865328,0.000267103,0.01257117,0.0005248712,0.000005755543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001563044,0.00003336978,0.9973261,0.00006302762,0.00001471809,0.00003740693,0.00001551577,0.0001718515,0.0007748767],"genre_scores_gemma":[0.1830614,0.00007511047,0.8121565,0.0001626978,0.00003293215,0.0004429504,0.000130744,0.0002331215,0.003704538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009488648,"threshold_uncertainty_score":0.03174269,"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."}}