{"id":"W2912720399","doi":"10.48550/arxiv.1901.09699","title":"Dynamic Measurement Scheduling for Event Forecasting using Deep RL","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Scheduling (production processes); Heuristic; Task (project management); Artificial intelligence; Machine learning; Operations research; Mathematical optimization; Economics; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001190179,0.0004160229,0.0004617869,0.0003480546,0.0003478092,0.0001558857,0.001946054,0.0003354626,0.000008680407],"category_scores_gemma":[0.0002144034,0.0005113313,0.0003416768,0.0004135454,0.00003926789,0.0002835092,0.002127507,0.000915273,0.0000232043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001500395,"about_ca_system_score_gemma":0.0006368214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002839817,"about_ca_topic_score_gemma":0.0001458696,"domain_scores_codex":[0.9969637,0.0002311815,0.000370734,0.001511628,0.0002596826,0.0006630567],"domain_scores_gemma":[0.9970092,0.0001906035,0.0005876761,0.001405833,0.0006121791,0.0001945753],"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":[0.00001787435,0.00003060721,0.003512481,0.0006187815,0.00006715568,0.00003467541,0.0002166156,0.9814319,0.00003042715,0.01185486,0.000003386804,0.002181256],"study_design_scores_gemma":[0.0004330008,0.0000657696,0.0003784617,0.0005274942,0.00006452403,0.000008560904,0.00006321819,0.9900059,0.00002148752,0.007831177,0.0001047767,0.0004957001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1636563,0.0002044393,0.8332787,0.0001215887,0.001409046,0.0008982025,0.000006382175,0.0002267753,0.0001986605],"genre_scores_gemma":[0.9206044,0.00001897907,0.07903598,0.00007301765,0.00007723273,0.000002817756,0.00001156053,0.00004227238,0.0001337342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7569481,"threshold_uncertainty_score":0.9997338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1949400643016283,"score_gpt":0.2483420644612013,"score_spread":0.05340200015957294,"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."}}