**化学**作为机器学**的重要分支, 是在与环境交互中寻找最优策略的一类方法.
**化学****年来与深度学**进行了广泛结合, 形成了深度**化学**的研究领域 …

Deep Reinforcement Learning (DRL) is a promising approach for general artificial
intelligence. However, most DRL methods suffer from the problem of data inefficiency. To …

In recent years, artificial intelligence has been widely used in modern construction, and
reinforcement learning methods have played an important role in it. The experience replay …

Natural disasters such as earthquakes have consecutive impacts on the smart grid because
of aftershock activities. To guarantee service requirements and smart grid stable operations …

In response to the high coupling of task interaction and many influencing factors in task
analysis, a task analysis method based on sequence decoupling and deep reinforcement …

To improve the anti-jamming performance of frequency hop** system in complex
electromagnetic environment, a Deep Q-Network algorithm with priority experience replay …

To address the problems of underutilization of samples and unstable training for intelligent
vehicle training in the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, a …

针对任务分析中任务协同交互耦合度高, 影响因素繁多等问题, 提出了基于序列解耦与深度**化
学**的任务分析方法, 实现了复杂约束条件下的任务分解及任务序列重构. 设计了基于任务信息 …

为解决无人机无模型路径规划的问题, 提出一种环境信息未知情况下基于势函数(PF)
奖赏的DQN 路径规划方法. 建立无人机在环境中的连续状态空间, 将360 等分成若干个角度作为 …

摘要基于深度**化学**的连续状态空间无人机隐蔽接敌问题, 提出了基于马尔可夫决策过程的
隐蔽接敌双深度Q 网络(DDQN) 方法. 利用DDQN 生成目标值函数的方法解决了传统DQN …