A reinforcement learning with evolutionary state recruitment strategy for autonomous mobile robots control
A reinforcement learning with evolutionary state recruitment strategy for autonomous mobile robots control
复制标题
DOI：
10.1016/j.robot.2003.11.006
复制
发表时间：
2003-09
期刊：
影响因子：
--
通讯作者：
T. Kondo;Koji Ito
中科院分区：
文献类型：
--
作者：
T. Kondo;Koji Ito
在最近的机器人领域，很多注意力都集中在利用强化学习（RL）设计机器人控制器，因为机器人将位于的环境应该是不可预测的人类设计师提前。然而，存在一些困难。其中之一是众所周知的“维数灾难问题”。因此，为了对复杂系统采用RL，不仅要考虑“适应性”，还要考虑“计算效率”。提出了一种基于NGnet的actor-critic强化学习的自适应状态招募策略。该策略使学习系统能够根据任务的复杂性和学习的进度，逐步重新排列/划分其状态空间。一些仿真结果和真实的机器人实现验证了该方法的有效性。
In recent robotics fields, much attention has been focused on utilizing reinforcement learning (RL) for designing robot controllers, since environments where the robots will be situated in should be unpredictable for human designers in advance. However there exist some difficulties. One of them is well known as ‘curse of dimensionality problem’. Thus, in order to adopt RL for complicated systems, not only ‘adaptability’ but also ‘computational efficiencies’ should be taken into account. The paper proposes an adaptive state recruitment strategy for NGnet-based actor-critic RL. The strategy enables the learning system to rearrange/divide its state space gradually according to the task complexity and the progress of learning. Some simulation results and real robot implementations show the validity of the method.