{"id":"W2900994167","doi":"","title":"A Fitted-Q Algorithm for Budgeted MDPs","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Algorithm; Mathematical optimization; Mathematics","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":[0.003782418,0.0015081,0.002858215,0.001216594,0.0008701415,0.001687861,0.003316856,0.004157971,0.01217827],"category_scores_gemma":[0.01536348,0.001567528,0.001170266,0.001356826,0.001785702,0.00189214,0.003325962,0.003369105,0.001536382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0019224,"about_ca_system_score_gemma":0.003683782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0108976,"about_ca_topic_score_gemma":0.008188355,"domain_scores_codex":[0.9986724,0.0005747839,0.00008067911,0.0002575053,0.0002444362,0.0001702013],"domain_scores_gemma":[0.9933938,0.004949928,0.0002478947,0.0002941058,0.0007179651,0.0003962812],"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":[0.0001180589,0.00006258651,0.0002331128,0.00008761036,0.00003241073,0.00004621292,0.00004056824,0.957713,0.0002280875,0.01066152,0.001407518,0.02936939],"study_design_scores_gemma":[0.00003454176,0.00001988153,0.00002006329,0.000009237283,0.00000395767,0.000005900567,0.000004500343,0.9948791,0.00005390159,0.004716024,0.0002493038,0.000003550323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007069193,0.000279191,0.9890214,0.0003450634,0.00009762215,0.0001288874,0.00009170577,0.0004189962,0.002547972],"genre_scores_gemma":[0.317608,0.0002855989,0.6731688,0.0003973289,0.0001378802,0.0008033079,0.0004425073,0.0003643747,0.006792179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01217827,"threshold_uncertainty_score":0.04074037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0166242353117175,"score_gpt":0.2425659507311312,"score_spread":0.2259417154194137,"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."}}