The invention discloses a satellite exploration control system and method based on deep reinforcement learning, the system comprises a reinforcement learning module and an environment module, the environment module comprises an action module, an initialization module, a state updating module, a basic environment module and a reward calculation module; the reinforcement learning module calls the initialization module, the initialization module initializes the basic environment, the initialization module returns to the current state after initialization is completed, and the reinforcement learning module outputs an action to the environment module after obtaining the current state; an action module in the environment module captures actions for processing, a state updating module calls a basic environment module to process current environment state updating, a reward calculation module obtains all state and action information and then gives a reward of current learning, and the reward and the updated state are transmitted to a reinforcement learning module; and the reinforcement learning module combines all the current information to form a tetrad and carries out training, and then outputs the next action according to the next state.
本发明公开了一种基于深度强化学习的卫星探索控制系统及方法,系统包括强化学习模块和环境模块,环境模块包括动作模块、初始化模块、状态更新模块、基础环境模块、奖励计算模块;强化学习模块调用初始化模块,初始化模块对基础环境进行初始化,完成初始化后由初始化模块返回当前状态,强化学习模块在获得当前状态后输出动作给环境模块;环境模块中的动作模块捕获动作进行处理,交由状态更新模块调用基础环境模块来处理当前环境状态更新,再由奖励计算模块获取所有状态和动作信息后给出当前这轮学习的奖励,并将奖励和更新后的状态传递给强化学习模块;强化学习模块结合当前所有的信息构成四元组并进行训练后,再根据下一步状态输出下一个动作。
Satellite exploration control system and method based on deep reinforcement learning
基于深度强化学习的卫星探索控制系统及方法
2023-09-05
Patent
Electronic Resource
Chinese
Satellite exploration control system and method based on deep reinforcement learning
European Patent Office | 2025
|Deep reinforcement learning based models for hard-exploration problems
European Patent Office | 2023
|Investigating exploration for deep reinforcement learning of concentric tube robot control
BASE | 2020
|