摘要
强化学习是通过对环境的反复试探建立起从环境状态到行为动作的映射。利用人工神经网络的反馈进行权值的调整,再与高学习效率的并行强化学习算法相结合,提出了基于人工神经网络的并行强化学习的应用方法,并通过实验仿真验证了迭代过程的收敛性和该方法的可行性,从而有效地完成了路径学习。
Reinforcement learning is an important class of learning techniques that learns to perform a certain task through trial and error interactions with an knowledge-poor environment.By combining artificial neural network with parallel reinforcement learning,an applicable method of parallel reinforcement learning algorithm based on artificial neural network is proposed.Experimental results show that the method is effective.
出处
《科学技术与工程》
2011年第4期756-759,共4页
Science Technology and Engineering
关键词
并行强化学习
BP神经网络
路径规划
Q学习
parallel reinforcement learning BP neural network path plan Q learning
