{"id":"W4312288984","doi":"10.1109/tcomm.2022.3225163","title":"Deep Reinforcement Learning for Resource Allocation in Multi-Band and Hybrid OMA-NOMA Wireless Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Communications","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Resource allocation; Wireless network; Mathematical optimization; Wireless; Greedy algorithm; Heuristic; Power control; Optimization problem; Spectral efficiency; Noma; Distributed computing; Channel (broadcasting); Power (physics); Algorithm; Mathematics; Artificial intelligence; Computer network; Telecommunications link; Telecommunications","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":[0.0002321901,0.0001697359,0.0001791732,0.000299173,0.0009861621,0.00003069219,0.0007934494,0.00005932021,0.00001551939],"category_scores_gemma":[0.00001136764,0.0002220719,0.00005481839,0.000397864,0.0001304187,0.000150279,0.0000262569,0.0008805858,0.000002007927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002844577,"about_ca_system_score_gemma":0.00001482016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002404809,"about_ca_topic_score_gemma":0.0002190976,"domain_scores_codex":[0.998955,0.0001275987,0.0003763258,0.0001886178,0.0001142453,0.0002382662],"domain_scores_gemma":[0.9980232,0.0004899964,0.00007786343,0.001326165,0.00004037128,0.00004240227],"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":[0.00001585227,0.00008689335,0.0000205582,0.0000118713,0.00002380459,2.30362e-7,0.0003441532,0.9542002,0.0005287445,0.0003471945,0.00003098992,0.04438949],"study_design_scores_gemma":[0.0007042443,0.00007073639,0.00007329757,0.0000223518,0.00001250797,0.000006939611,0.001215193,0.9863269,0.002798093,0.00009174437,0.008462816,0.0002152237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006502217,0.001055601,0.990198,0.0006762461,0.00007210641,0.0006244046,0.000006859316,0.0006186906,0.0002459298],"genre_scores_gemma":[0.9878104,0.002379446,0.007169265,0.00005572825,0.000003542946,0.002315137,0.00007567358,0.00005185168,0.0001389684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9830287,"threshold_uncertainty_score":0.9055828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.026820198413611,"score_gpt":0.2564614589231429,"score_spread":0.2296412605095319,"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."}}