{"id":"W3166948032","doi":"10.48550/arxiv.2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Age of Information Optimization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Successor cardinal; Reinforcement learning; Representation (politics); Computer science; Sampling (signal processing); Artificial intelligence; Bridge (graph theory); Machine learning; Simple random sample; Reinforcement; Variety (cybernetics); Mathematics; Engineering; Detector; Sociology; Law; Political science","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":[0.001937319,0.0009316045,0.001679998,0.0006252388,0.0004041219,0.0009421998,0.002192813,0.001153499,0.003399151],"category_scores_gemma":[0.007741715,0.0005312114,0.000532401,0.0005788562,0.001336822,0.001704096,0.00170141,0.002420574,0.0004022988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001321236,"about_ca_system_score_gemma":0.001904221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003703102,"about_ca_topic_score_gemma":0.004568234,"domain_scores_codex":[0.9991335,0.0003607175,0.00003445669,0.00017218,0.0001973496,0.0001017598],"domain_scores_gemma":[0.9971913,0.001902954,0.0001957568,0.000230206,0.0002911282,0.000188643],"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":[0.0001757334,0.0001533853,0.001453256,0.0001036444,0.000065459,0.00009475378,0.00008614128,0.8524188,0.001835858,0.05179756,0.003256152,0.0885593],"study_design_scores_gemma":[0.000009825643,0.00001908773,0.00003720603,0.000005184421,0.000004083457,0.000008221322,0.000002221954,0.9902166,0.0002353854,0.009242525,0.0002166457,0.00000307617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01143981,0.0002603678,0.9859309,0.0002503183,0.00005636382,0.00005708568,0.00005535108,0.000407266,0.001542431],"genre_scores_gemma":[0.7456163,0.0002660835,0.2489243,0.0003582451,0.0001352032,0.0002893819,0.0002249589,0.0001781009,0.004007357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003703102,"threshold_uncertainty_score":0.01137131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05722262922684172,"score_gpt":0.1976967943510086,"score_spread":0.1404741651241669,"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."}}