logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

PC-Gym: Benchmark environments for process control problems

delete2025-08-30
delete0
PRE
AI
M
Maximilian Bloor
J
José Torraca
I
Ilya Orson Sandoval
A
Akhil Ahmed
M
Martha White
M
Mehmet Mercangöz
C
Calvin Tsay
E
Ehecatl Antonio Del Rio Chanona
M
Max Mowbray *
DOI：10.1016/j.compchemeng.2025.109363delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• PC-Gym provides benchmark environments for testing reinforcement learning in process control. • Features customizable disturbances, constraints, and reward functions for realistic scenarios. • Benchmarks RL algorithms against NMPC oracle across multiple chemical process environments. • Open-source tool bridges gap between theoretical RL and practical process control applications.
Keywords:
PC-Gym
reinforcement learning
process control
benchmarking
NMPC
open-source tool

Journal

C
Computers and Chemical Engineering
IF:
3.9
Papers:
8.1K
Citations:
1.7W

Organization

U
university of alberta
Scholars:
5.1W
Papers: 4.9W
Citations: 65
I
Imperial College London
Scholars:
8.3W
Papers: 7.3W
Citations: 11.1W