mlsanityData to 7 Oct 2026

A Meta-Reinforcement Learning Approach to Process Control

arXiv 2103.14060 ↗First posted 25 Mar 2021cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related tasks. In essence, models are being trained to learn new tasks effectively rather than master a single task. Meta-learning is appealing for process control applications because the perturbations to a process required to train an AI controller can be costly and unsafe. Additionally, the dynamics and control objectives are similar across many different processes, so it is feasible to create a generalizable controller through meta-learning capable of quickly adapting to different systems. In this work, we construct a deep reinforcement learning (DRL) based controller and meta-train the controller using a latent context variable through a separate embedding neural network. We test our meta-algorithm on its ability to adapt to new process dynamics as well as different control objectives on the same process. In both cases, our meta-learning algorithm adapts very quickly to new tasks, outperforming a regular DRL controller trained from scratch. Meta-learning appears to be a promising approach for constructing more intelligent and sample-efficient controllers.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

14 of 23 references.

References · 14

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  6. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  7. 2016Learning to learn by gradient descent by gradient descentcited by 616
  8. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  9. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  10. 2016Learning to reinforcement learncited by 369
  11. 2018ProMP: Proximal Meta-Policy Searchcited by 91
  12. 2019Guided Meta-Policy Searchcited by 26
2 more
  1. 2019Reinforcement Learning for Batch Bioprocess Optimizationcited by 24
  2. 2020Deep Reinforcement Learning for Process Control: A Primer for Beginnerscited by 15

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 1.

5 papers.

  1. 2021Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuningcited by 18
  2. 2021Safe Chance Constrained Reinforcement Learning for Batch Process Controlcited by 10
  3. 2022Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approachcited by 10
  4. 2022Meta-Reinforcement Learning for Adaptive Control of Second Order Systemscited by 1
  5. 2024Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Overview and Perspectivescited by 0