And artificial neural network is a valid method to solve the generalization problem for the continuous state and action pairs in the reinforcement learning method.
针对强化学习在连续状态和动作空间的泛化问题,人工神经网络是一种有效的解决方法。
In order to describe the process of multi action commitments and uncommitments, the concept of transition between model state pairs in action dynamic logic was introduced.
通过引入动态逻辑中模型状态迁移概念以及相关谓词来描述多动作承诺与取消承诺时各模型状态变化及相应处理 。
应用推荐