Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach
arXiv:2203.09661 · doi:10.1016/j.jprocont.2022.08.002
Abstract
Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning. In this work, we formulate a meta reinforcement learning (meta-RL) control strategy that can be used to tune proportional--integral controllers. Our meta-RL agent has a recurrent structure that accumulates "context" to learn a system's dynamics through a hidden state variable in closed-loop. This architecture enables the agent to automatically adapt to changes in the process dynamics. In tests reported here, the meta-RL agent was trained entirely offline on first order plus time delay systems, and produced excellent results on novel systems drawn from the same distribution of process dynamics used for training. A key design element is the ability to leverage model-based information offline during training in simulated environments while maintaining a model-free policy structure for interacting with novel processes where there is uncertainty regarding the true process dynamics. Meta-learning is a promising approach for constructing sample-efficient intelligent controllers.
arXiv comment23 pages; postprint
References in corpus (7)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Addressing Function Approximation Error in Actor-Critic Methods
- Learning Quadrupedal Locomotion over Challenging Terrain
- RL: Fast Reinforcement Learning via Slow Reinforcement Learning
- Deep Reinforcement Learning for Process Control: A Primer for Beginners
- Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning
- A Meta-Reinforcement Learning Approach to Process Control