Reinforcement Learning in System Identification

Jose Antonio Martin H., Oscar Fernández Vicente, Sergio Perez, Anas Belfadil, Cristina Ibanez-Llano, Freddy José Perozo Rondón, Jose Javier Valle, Javier Arechalde Pelaz

Keywords: System Identification, Reinforcement Learning, Offline Reinforcement Learning, Forward Models

TL;DR: In this paper, we propose the use of Reinforcement Learning in the System Identification problem

Abstract: System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement Learning research, where forward models approximate the state transition function of a Markov Decision Process by learning a mapping function from current state and action to the next state. This problem is commonly defined as a Supervised Learning problem in a direct way. This common approach faces several difficulties due to the inherent complexities of the dynamics to learn, for example, delayed effects, high non-linearity, non-stationarity, partial observability and, more important, error accumulation when using bootstrapped predictions (predictions based on past predictions), over large time horizons. Here we explore the use of Reinforcement Learning in this problem. We elaborate on why and how this problem fits naturally and sound as a Reinforcement Learning problem, and present some experimental results that demonstrate RL is a promising technique to solve these kind of problems.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2212.07123/code)