ID 原文 译文
40886 因此，改善样本利用率是拓展深度强化学习应用范围的关键。 Therefore, improving sample utilization is the key to expand the application scope of deep reinforcement learning.
40887 除了基于模型的方法之外，智能体的探索策略也是影响样本利用率的重要因素。 In addition to the model-based approaches, the exploration strategy of the agent is also an important factor affecting the sample utilization.
40888 本文在智能体的行为策略中引入基于记忆的探索方法，其可以通过搜索过去的记忆来快速产生高回报的样本供状态价值网络学习，加快算法的训练过程。 A memory-based exploration method is introduced into the agent's behavior strategy in this paper, which can quickly generate high return sample supply state value network learning by searching past memory, and speed up the training process of the algorithm.
40889 通过在仿真环境中利用基准任务来对所提算法进行评测，验证了其有效性。 The effectiveness of the proposed algorithm is verified by using the benchmark task in the simulation environment.
40890 针对无线传感器网络节点能耗不均衡，网络生存期短等问题，提出一种基于人工蜂群算法的能量高效分簇路由协议。 In order to solve the problems of uneven energy consumption of sensor nodes and short lifetime of sensor networks in wireless sensor networks, an energy-efficient clustering routing protocol based on artificial bee colony algorithm is proposed.
40891 在簇头选举阶段，通过定义簇头的能量因子、位置因子和向心率因子设计高效的适应度函数，评估人工蜂群算法生成的解的质量，选出最优簇头。 In the cluster head selection phase, the energy factor, location factor and centripetal factor are defined for the cluster head, thus an efficient fitness function is designed to evaluate the quality of the solution generated by the artificial bee colony algorithm, so as to select the optimal cluster head set.
40892 在稳定传输阶段，提出一种基于最小生成树的高效路由算法，通过在每个簇头和基站之间寻找合适的路径来平衡并降低网络能耗。 In the stable transmission phase, an efficient routing algorithm based on minimum spanning tree is proposed to balance and reduce network energy consumption by finding a suitable path between each cluster head and the base station.
40893 为进一步提高网络吞吐量，将区分忙闲节点的轮询控制机制引入簇内通信。 In order to further improve the network throughput, a polling control mechanism based on busy/idle nodes is introduced into intra-cluster communication phase.
40894 在不同规模的场景中对所提协议的性能进行了评估， The performance of the proposed protocol is evaluated in several scenarios with different characteristics.
40895 仿真测试结果表明，与KUCR协议、FIGWO协议相比，基于人工蜂群算法的分簇路由协议能够有效地延长网络生存期，提高网络吞吐量。 Simulation results show that, compared with KUCR protocol and FIGWO protocol, the proposed protocol can effectively prolong the network lifetime and improve the network throughput.