Adaptive Risk Sensitive Model Predictive Control with Stochastic Search
Adaptive Risk Sensitive Model Predictive Control with Stochastic Search
复制标题
DOI：
--
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Ziyi Wang;Oswin So;Keuntaek Lee;Evangelos A. Theodorou
中科院分区：
文献类型：
--
作者：
Ziyi Wang;Oswin So;Keuntaek Lee;Evangelos A. Theodorou
我们提出了一个通用的框架，优化动态系统的条件风险值使用随机搜索。该框架能够处理来自初始条件、随机动态和模型中不确定参数的不确定性。该算法与风险敏感的分布式强化学习框架进行了比较，并在具有随机动态的钟摆和cartpole上表现出优异的性能。我们还展示了该框架的适用性，机器人作为一个自适应的风险敏感控制器，通过优化相对于完全非线性的信念，由粒子滤波器上的钟摆，cartpole，和四轴飞行器在模拟。
We present a general framework for optimizing the Conditional Value-at-Risk for dynamical systems using stochastic search. The framework is capable of handling the uncertainty from the initial condition, stochastic dynamics, and uncertain parameters in the model. The algorithm is compared against a risk-sensitive distributional reinforcement learning framework and demonstrates outperformance on a pendulum and cartpole with stochastic dynamics. We also showcase the applicability of the framework to robotics as an adaptive risk-sensitive controller by optimizing with respect to the fully nonlinear belief provided by a particle filter on a pendulum, cartpole, and quadcopter in simulation.