Average Cost Optimal Control of Stochastic Systems Using Reinforcement Learning

no code implementations • 13 Oct 2020 • Jing Lai, Junlin Xiong

By using Q-function, we propose an online learning scheme to estimate the kernel matrix of Q-function and to update the control gain using the data along the system trajectories.

reinforcement-learning Reinforcement Learning (RL)

Model-free optimal control of discrete-time systems with additive and multiplicative noises

no code implementations • 20 Aug 2020 • Jing Lai, Junlin Xiong, Zhan Shu

This paper investigates the optimal control problem for a class of discrete-time stochastic systems subject to additive and multiplicative noises.

Reinforcement Learning (RL)