{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001635052,0.0006923536,0.0008219249,0.0002959249,0.0003067954,0.0005151923,0.0009256591,0.0007903591,0.001707462],"category_scores_gemma":[0.0040357,0.000239873,0.0003091741,0.0002359623,0.000760192,0.0008276855,0.0007647951,0.001228812,0.0002285925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006917887,"about_ca_system_score_gemma":0.001145293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006217526,"about_ca_topic_score_gemma":0.002617535,"domain_scores_codex":[0.9995548,0.0001470183,0.00002208016,0.00008432069,0.00008139321,0.0001103658],"domain_scores_gemma":[0.9978478,0.001393802,0.0002159007,0.0001663559,0.0002236242,0.0001525619],"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":[0.0001648196,0.0001547807,0.0006709969,0.00003009217,0.00001816114,0.00006170428,0.00003895732,0.9699545,0.001994719,0.001407665,0.0002731397,0.02523047],"study_design_scores_gemma":[0.000009558938,0.0000404513,0.00006323538,0.000001522772,0.000002279627,0.000004583806,0.000004106953,0.9987279,0.0006288438,0.0004548227,0.00006048526,0.000002258877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3688846,0.0005018529,0.6225699,0.0004018962,0.0001171199,0.0001736347,0.00005384645,0.002261398,0.005035755],"genre_scores_gemma":[0.9774199,0.00003968174,0.02194688,0.0000507977,0.000008291831,0.00003380805,0.00002154708,0.00001719327,0.0004620168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006217526,"threshold_uncertainty_score":0.01236272,"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."}}