Before we can find a model, we must forget about perfection

TL;DR

This paper argues that pursuing a perfect world model in reinforcement learning is impractical and proposes focusing on multiple simple Event-Driven models as a more feasible alternative.

Contribution

It introduces Event-Driven models as a generalization of MDPs and advocates for searching multiple simple models instead of a single perfect one.

Findings

Perfect models are too complex and impossible to find.

Event-Driven models generalize MDPs for better practicality.

Using multiple simple models improves understanding of the environment.

Abstract

With Reinforcement Learning we assume that a model of the world does exist. We assume furthermore that the model in question is perfect (i.e. it describes the world completely and unambiguously). This article will demonstrate that it does not make sense to search for the perfect model because this model is too complicated and practically impossible to find. We will show that we should abandon the pursuit of perfection and pursue Event-Driven (ED) models instead. These models are generalization of Markov Decision Process (MDP) models. This generalization is essential because nothing can be found without it. Rather than a single MDP, we will aim to find a raft of neat simple ED models each one describing a simple dependency or property. In other words, we will replace the search for a singular and complex perfect model with a search for a large number of simple models.