Provable Reinforcement Learning for Networked Control Systems with Stochastic Packet Disordering

no code implementations • 5 Dec 2023 • Wenqian Xue, Yi Jiang, Frank L. Lewis, Bosen Lian

This paper formulates a stochastic optimal control problem for linear networked control systems featuring stochastic packet disordering with a unique stabilizing solution certified.

Q-Learning reinforcement-learning

Data-Driven Inverse Reinforcement Learning for Expert-Learner Zero-Sum Games

no code implementations • 5 Jan 2023 • Wenqian Xue, Bosen Lian, Jialu Fan, Tianyou Chai, Frank L. Lewis

In this paper, we formulate inverse reinforcement learning (IRL) as an expert-learner interaction whereby the optimal performance intent of an expert or target agent is unknown to a learner agent.

reinforcement-learning Reinforcement Learning (RL)