Event-Driven Models

TL;DR

This paper proposes event-driven models as a generalization of action-driven models in reinforcement learning, emphasizing their sustainability and predictability by updating states only upon specific events.

Contribution

It introduces event-driven models as a novel approach that extends action-driven models, highlighting their advantages in stability and predictability.

Findings

Event-driven models change states only upon specific events.

They are more sustainable than action-driven models.

Event-driven models offer greater predictability due to rare event occurrence.

Abstract

In Reinforcement Learning we look for meaning in the flow of input/output information. If we do not find meaning, the information flow is not more than noise to us. Before we are able to find meaning, we should first learn how to discover and identify objects. What is an object? In this article we will demonstrate that an object is an event-driven model. These models are a generalization of action-driven models. In Markov Decision Process we have an action-driven model which changes its state at each step. The advantage of event-driven models is their greater sustainability as they change their states only upon the occurrence of particular events. These events may occur very rarely, therefore the state of the event-driven model is much more predictable.