Supervised Imitation Training for Deep Reinforcement Learning Control of a Fluid Catalytic Cracking System
作者单位：Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial SystemsSchool of Engineering Huzhou University
会议名称：《第43届中国控制会议》
会议日期：1000年
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081705[工学-工业催化] 081104[工学-模式识别与智能系统] 08[工学] 0817[工学-化学工程与技术] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
关 键 词：Reinforcement learning Fluid catalytic cracking PID controller supervised imitation training
摘 要：Reinforcement Learning(RL) based intelligent automation techniques have been widely applied in various industrial sectors, ranging from unmanned aerial vehicles to autonomous driving vehicles. However, training a sophisticated RL controller for the industry-level application is usually time-consuming and expensive. To tackle this challenge, a supervised imitation training approach is proposed in this work. This approach utilizes state-of-art industrial controllers, particularly the PID controllers, to facilitate training RL controllers. The actor network within the RL controller is pre-trained by fitting the data which are collected from traditional controllers. As a result, the agent at first behaves similarly to the conventional controller, but its performance could be improved during the online stage for training the RL agent. Experiments were conducted for a simulated fluid catalytic cracking, where the effectiveness of the supervised imitation approach is verified.