Safety-Aware Reinforcement Learning Framework with an Actor-Critic-Barrier Structure
Safety-Aware Reinforcement Learning Framework with an Actor-Critic-Barrier Structure
复制标题
DOI：
10.23919/acc.2019.8815335
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Yongliang Yang;Yixin Yin;Wei He;K. Vamvoudakis;H. Modares;D. Wunsch
中科院分区：
文献类型：
--
作者：
Yongliang Yang;Yixin Yin;Wei He;K. Vamvoudakis;H. Modares;D. Wunsch
本文研究了同时具有全状态约束和控制输入约束的控制问题。首先，提出了一种新的基于障碍函数的系统转换方法，以保证系统的全状态约束。为了处理输入饱和问题，对控制输入施加了双曲线型惩罚函数。将基于行动者-批评者的强化学习技术与障碍变换相结合，学习同时考虑全状态约束和输入饱和的最优控制策略。为了验证该算法的有效性，最后进行了数值仿真。
This paper considers the control problem with constraints on full-state and control input simultaneously. First, a novel barrier function based system transformation approach is developed to guarantee the full-state constraints. To deal with the input saturation, the hyperbolic-type penalty function is imposed on the control input. The actor-critic based reinforcement learning technique is combined with the barrier transformation to learn the optimal control policy that considers both the full-state constraints and input saturations. To illustrate the efficacy, a numeric simulation is implemented in the end.