Safe Exploration Algorithms for Reinforcement Learning Controllers

Self-learning approaches, such as reinforcement learning, offer new possibilities for autonomous control of uncertain or time-varying systems. However, exploring an unknown environment under limited prediction capabilities is a challenge for a learning agent. If the environment is dangerous, free exploration can result in physical damage or in...

Incremental Model Based Actor Critic Design for Optimal Adaptive Flight Control: Investigation and Implementation of Online Flight Control Methods

To solve the problem of optimal control for nonlinear system, Actor Critic Designs (ACD) can be utilized which use the concept of Reinforcement learning (RL) and function approximators such as Neural networks (NN). Traditional ACD methods require a model NN that needs to be trained offline. Recently, research focus has been shifted to model-free...

Model-free motion control of positioning stage

Driven by the rise of market demand and development of technology, high-precision motion systems must meet the increasing accuracy requirement. Currently, High-precision positioning stage is widely used in many different application areas, such as hard disk drives, wafer steppers and electron and atomic force microscopes for nano-scale imaging....