{"id":"W4327785466","doi":"10.1109/tnsm.2023.3258692","title":"Accelerating Reinforcement Learning via Predictive Policy Transfer in 6G RAN Slicing","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Energy Harvesting in Wireless Networks","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Slicing; Ran; Transfer of learning; Transfer (computing); Predictive power; Artificial intelligence; Computer network; World Wide Web; Parallel computing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003076792,0.0002809545,0.0002404868,0.0003692954,0.0003013331,0.00007391391,0.000150274,0.0001076115,0.0000227106],"category_scores_gemma":[9.210947e-7,0.0003168944,0.00005383248,0.001645632,0.00001709783,0.0001653779,0.000005825715,0.0005025413,0.0000240444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001383134,"about_ca_system_score_gemma":0.00000833852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001837984,"about_ca_topic_score_gemma":0.0006241978,"domain_scores_codex":[0.9983922,0.00006282148,0.0003846527,0.0003174966,0.0002279775,0.0006148462],"domain_scores_gemma":[0.9995253,0.0001263461,0.00002084284,0.0002053297,0.00002161118,0.000100585],"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":[0.00002742864,0.00001342968,0.0000442288,0.0002012485,0.0001133843,0.0000181398,0.00100194,0.9511074,0.00005576089,0.0001729854,0.00005605891,0.047188],"study_design_scores_gemma":[0.0007140519,0.00006094294,0.0007390616,0.0003612704,0.00004191916,0.000002199679,0.0004045342,0.9962454,0.0001472946,0.00004860226,0.0009505943,0.0002841052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08466588,0.00005015096,0.8999563,0.0002985371,0.0005768891,0.0004961042,0.000001431386,0.001219956,0.0127347],"genre_scores_gemma":[0.9967376,0.001563199,0.0004385245,0.0003677609,0.0002331598,0.0002037902,0.00001250658,0.00007393859,0.0003695168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9120717,"threshold_uncertainty_score":0.9999283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01196982028629463,"score_gpt":0.2115837783203796,"score_spread":0.199613958034085,"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."}}