Long Term Evolution; approximation theory; learning (artificial intelligence); learning automata; multilayer perceptrons; optimisation; telecommunication computing; telecommunication scheduling; CACLA RL; GPF scheduling rule; LTE scheduling; MLPNN; TTI; adaptive proportional fair parameterization optimization problem; continuous actor-critic reinforcement learning; generalized proportional fair scheduling rule; multilayer perceptron neural network; nonlinear function approximation; system throughput maximization; transmission time interval; user fairness satisfaction; Aerospace electronics; Measurement; Optimal scheduling; Throughput; Training; Wireless communication; CACLA-1; CACLA-2; CQI; GPF; LTE-A; MLPNN; RL; TTI; fairness; policy; scheduling rule; throughput;
机译:基于深度学习的基于学习的比例公平调度控制方案D2D通信
机译:LTE下行分组调度中基于延迟的加权比例公平算法
机译:基于比例公平调度数学建模的LTE Hetnet小区选择新程序
机译:基于自适应比例公平参数化LTE调度使用连续演员 - 批评加强学习
机译:火星:多可扩展的演员 - 评论家强化学习调度员
机译:使用带有尖峰神经元的连续时间Actor-Critic框架进行强化学习
机译:基于VRFT的自适应演员 - 评论家的数据驱动的无模型跟踪强化学习控制