Composite adaptation and learning techniques were initially proposed for improving
parameter convergence in adaptive control and have generated considerable research …

In this article, we propose a way to enhance the learning framework for zero-sum games
with dynamics evolving in continuous time. In contrast to the conventional centralized actor …

Continual lifelong learning is an machine learning framework inspired by human learning,
where learners are trained to continuously acquire new knowledge in a sequential manner …

In this paper, a control scheme is designed for the trajectory tracking problem of
underactuated autonomous underwater vehicles with input saturation, parameter …

In this article, a decentralized event-triggered control mechanism is established to solve the
interconnected issue of continuous-time nonlinear systems with asymmetric input constraints …

In this article, we propose RRT-Q, an online and intermittent kinodynamic motion planning
framework for dynamic environments with unknown robot dynamics and unknown …

We focus on learning the zero-constraint-violation safe policy in model-free reinforcement
learning (RL). Existing model-free RL studies mostly use the posterior penalty to penalize …

Optimal control of nonlinear systems by using adaptive dynamic programming (ADP)
methods is always a hot topic in recent years. However, unknown nonlinear systems with …

This article concentrates on the non‐zero‐sum games problem of discrete‐time Markov
jump systems without requiring the system dynamics information. First, the multiplayer non …

There exist universal model uncertainty and input deadzone in mechatronic motion plant
due to unknown model parameters and actuator physical feature, which will degrade the …