Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming

TL;DR

This paper presents a novel genetic programming approach, FGPRL, for automatically generating interpretable fuzzy controllers using reinforcement learning and model-based predictions, outperforming particle swarm methods in industrial benchmarks.

Contribution

Introduces FGPRL, a new method combining genetic programming and reinforcement learning to automatically design interpretable fuzzy controllers with optimized parameters.

Findings

FGPRL can autonomously learn effective fuzzy policies.

FGPRL outperforms FPSRL in control performance.

The method automatically determines fuzzy rule set size and features.

Abstract

Autonomously training interpretable control strategies, called policies, using pre-existing plant trajectory data is of great interest in industrial applications. Fuzzy controllers have been used in industry for decades as interpretable and efficient system controllers. In this study, we introduce a fuzzy genetic programming (GP) approach called fuzzy GP reinforcement learning (FGPRL) that can select the relevant state features, determine the size of the required fuzzy rule set, and automatically adjust all the controller parameters simultaneously. Each GP individual's fitness is computed using model-based batch reinforcement learning (RL), which first trains a model using available system samples and subsequently performs Monte Carlo rollouts to predict each policy candidate's performance. We compare FGPRL to an extended version of a related method called fuzzy particle swarm reinforcement learning (FPSRL), which uses swarm intelligence to tune the fuzzy policy parameters. Experiments using an industrial benchmark show that FGPRL is able to autonomously learn interpretable fuzzy policies with high control performance.