Simultaneous Process Design and Control Optimization using Reinforcement Learning

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...

Actor-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-...

Lyapunov 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. ...

Function 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...

Incremental optimization of FIS using reinforcement learning