{"id":32,"date":"2023-12-12T21:46:56","date_gmt":"2023-12-12T21:46:56","guid":{"rendered":"https:\/\/sites.tntech.edu\/lcasl\/?page_id=32"},"modified":"2023-12-13T17:45:21","modified_gmt":"2023-12-13T17:45:21","slug":"stochastic-methods","status":"publish","type":"page","link":"https:\/\/sites.tntech.edu\/lcasl\/stochastic-methods\/","title":{"rendered":"Stochastic Methods"},"content":{"rendered":"\n
<\/div>\n\n\n\n
\n

Adaptive Risk Sensitive Path Integral for Model Predictive Control via Reinforcement Learning<\/h3>\n<\/div>\n\n\n\n
\n
\n
\n

We propose a reinforcement learning framework where an agent uses an internal nominal model for stochastic model predictive control (MPC) while compensating for a disturbance. Our work builds on the existing risk-aware optimal control with stochastic differential equations (SDEs) that aims to deal with such disturbance. However, the risk sensitivity and the noise strength of the nominal SDE in the risk-aware optimal control are often heuristically chosen. In the proposed framework, the risk-taking policy determines the behavior of the MPC to be risk-seeking (exploration) or risk-averse (exploitation). Specifically, we employ the risk-aware path integral control that can be implemented as a Monte-Carlo (MC) sampling with the fast parallel simulations using a GPU. The MC sampling implementations of the MPC have been successful in robotic applications due to its real-time computation capability. The proposed framework that adapts the noise model and the risk sensitivity outperforms the standard model predictive path integral in simulation environments that have disturbances.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

UAV Simulation with Double Integrator Kinematics<\/h3>\n\n\n\n