Simultaneous Process Design and Control Optimization using Reinforcement Learning
نویسندگان
چکیده
Abstract The performance of a chemical plant is highly affected by its design and control. A cannot be accurately evaluated without controls vice versa. To optimally address control simultaneously, one must formulate bi-level mixed-integer nonlinear program with dynamic optimization problem as the inner problem; this intractable. However, computing an optimal policy using reinforcement learning, controller closed-form expression can computed embedded into mathematical program. In work, approach that uses gradient method to compute policy, which then proposed. tested in tank case study evaluated. It shown proposed outperforms current state-of-the-art strategies. This opens whole new range possibilities simultaneous engineering systems.
منابع مشابه
Recent advances in optimization-based simultaneous process and control design
This paper is one outcome of my very productive collaboration with Stratos Pistikopoulos while we were both at Imperial College London. It presents an attempt to take a truly integrated approach to the design of a process and its control system. Based on an optimisation framework, the paper illustrates the complexities involved in implementing a fully integrated approach to this challenging pro...
متن کاملActor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback
This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many humanmachine interaction settings, there is a growing gap between the degrees-...
متن کاملLyapunov Design for Safe Reinforcement Learning Control
We propose a general approach to safe reinforcement learning control based on Lyapunov design methods. In our approach, a Lyapunov function—a special form of domain knowledge—is used to formulate the action choices available to a reinforcement learning agent. A learning agent choosing among these actions provably enjoys performance guarantees, and satisfies safety constraints of various kinds. ...
متن کاملFunction Optimization Using Connectionist Reinforcement Learning Algorithms
Any nonassociative reinforcement learning algorithm can be viewed as a method for performing function optimization through (possibly noise-corrupted) sampling of function values. We describe the results of simulations in which the optima of several deterministic functions studied by Ackley (1987) were sought using variants of REINFORCE algorithms (Williams, 1987; 1988). Some of the algorithms u...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IFAC-PapersOnLine
سال: 2021
ISSN: ['2405-8963', '2405-8971']
DOI: https://doi.org/10.1016/j.ifacol.2021.08.293