Adaptive optics control using model-based reinforcement learning

Model-based Control in Adaptive Optics Systems

Acknowledgments D uring the past five years, I have got generous and continuous support and encouragement from my supervisors, colleagues, friends, and my family. I am really in a luxury situation because there are so many people around. I'd like to express my sincere gratitude to you all! Special thanks to my supervisor — Prof. Michel Verhaegen! First of all, thanks for offering me the opportu...

Adaptive Abstraction for Model-Based Reinforcement Learning

This paper presents a novel model-based reinforcement learning framework called the Adaptive Modelling and Planning System (AMPS). The challenge of a model-based reinforcement learning agent is using experience in the world to generate a model. In problems with large state and action spaces, the agent must generalise from limited experience by grouping together similar states and actions, effec...

Experience-based model predictive control using reinforcement learning

Reinforcement Learning Based PID Control of Wind Energy Conversion Systems

In this paper an adaptive PID controller for Wind Energy Conversion Systems (WECS) has been developed. Theadaptation technique applied to this controller is based on Reinforcement Learning (RL) theory. Nonlinearcharacteristics of wind variations as plant input, wind turbine structure and generator operational behaviordemand for high quality adaptive controller to ensure both robust stability an...

Efficient reinforcement learning: model-based Acrobot control

|Several methods have been proposed in the reinforcement learning literature for learning optimal policies for sequential decision tasks. Q-learning is a model-free algorithm that has recently been applied to the Acrobot, a two-link arm with a single actuator at the elbow that learns to swing its free endpoint above a target height. However, applying Q-learning to a real Acrobot may be impracti...