{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001793936,0.000100102,0.00009511661,0.0000794767,0.0002914472,0.0001659229,0.0004772635,0.00002978744,0.00002659718],"category_scores_gemma":[0.00004954694,0.00008546418,0.00003683249,0.001265782,0.00002710176,0.00105955,0.0002051144,0.0001144249,0.00002747025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000944541,"about_ca_system_score_gemma":0.00006665794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001478137,"about_ca_topic_score_gemma":0.00001263992,"domain_scores_codex":[0.9991647,0.00006872334,0.0001287941,0.0003332719,0.000121905,0.0001826095],"domain_scores_gemma":[0.9990146,0.00005426922,0.0001561082,0.0004598802,0.000242593,0.00007257977],"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":[0.00002032348,0.00001049175,0.001406388,0.00000598948,0.00001468176,0.00001512033,0.0008876214,0.9206933,0.00001599718,0.07669377,0.000051279,0.0001850064],"study_design_scores_gemma":[0.0004119586,0.00002730564,0.0008992914,0.000009341168,0.00001117149,0.00001145201,0.0009550577,0.9965599,0.0001845548,0.0001826767,0.0006157603,0.0001315971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02744582,0.00000778849,0.95911,0.0003275519,0.00002823069,0.0001834133,8.084092e-8,0.0001002658,0.01279682],"genre_scores_gemma":[0.9559463,0.00001411144,0.0415055,0.0003274816,0.00001392062,0.000002248079,0.0000171468,0.000005995313,0.002167242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9285005,"threshold_uncertainty_score":0.3485128,"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."}}