{"id":"W3017289904","doi":"10.48550/arxiv.2004.07911","title":"A Deep Reinforcement Learning Approach for Dynamic Contents Caching in HetNets","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Age of Information Optimization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Cache; Reinforcement learning; Markov decision process; Scheduling (production processes); Performance metric; Dynamic web page; Exploit; Queue; Distributed computing; Computer network; Markov process; Artificial intelligence; Web service; World Wide Web; Mathematical optimization","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":[0.0002233824,0.0002419391,0.0002747216,0.000308093,0.0001444556,0.0001464896,0.001154617,0.0001892517,0.000005142738],"category_scores_gemma":[0.00007189295,0.0003028053,0.0001320714,0.0004022827,0.00002883882,0.0007834697,0.0009590187,0.0005380052,0.00001508995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004440607,"about_ca_system_score_gemma":0.00008184399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005139818,"about_ca_topic_score_gemma":0.00001304196,"domain_scores_codex":[0.9985692,0.00007950776,0.0003092624,0.0006472058,0.0001037465,0.000291082],"domain_scores_gemma":[0.9988757,0.00005100788,0.000388821,0.0004453,0.0001295388,0.0001095968],"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":[0.00002438913,0.00001864924,0.0002390382,0.00010488,0.00002653435,0.00001573713,0.001110323,0.9806874,0.000004571902,0.01742366,0.00001363886,0.0003311875],"study_design_scores_gemma":[0.0008078386,0.00004574337,0.0001702602,0.00005180702,0.00001408559,0.000001499733,0.0001966272,0.9971657,0.000007788765,0.001204493,0.00004200619,0.0002921438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006545065,0.00001360962,0.9893839,0.00007902023,0.0001546553,0.0007475635,0.000001058542,0.0001962433,0.002878923],"genre_scores_gemma":[0.9661424,0.00004602738,0.03301156,0.0001350662,0.000013948,0.000005888174,0.0001552029,0.00001450702,0.000475363],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9595973,"threshold_uncertainty_score":0.9999424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05901472695652191,"score_gpt":0.1909263667093481,"score_spread":0.1319116397528262,"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."}}