Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics
Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics
复制标题
DOI：
10.1109/icra48506.2021.9560886
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Ya-Chien Chang;Sicun Gao
中科院分区：
文献类型：
--
作者：
Ya-Chien Chang;Sicun Gao
缺乏稳定性保证限制了基于学习的方法在机器人核心控制问题中的实际应用。我们开发了新的方法学习神经控制策略和神经李雅普诺夫批评功能的无模型强化学习（RL）设置。我们使用基于样本的方法和几乎李雅普诺夫函数条件，通过学习的李雅普诺夫临界函数来估计吸引区域和不变性。该方法增强了神经控制器的稳定性，用于各种非线性系统，包括汽车和四旋翼控制。
The lack of stability guarantee restricts the practical use of learning-based methods in core control problems in robotics. We develop new methods for learning neural control policies and neural Lyapunov critic functions in the modelfree reinforcement learning (RL) setting. We use sample-based approaches and the Almost Lyapunov function conditions to estimate the region of attraction and invariance properties through the learned Lyapunov critic functions. The methods enhance stability of neural controllers for various nonlinear systems including automobile and quadrotor control.