Authors: Dimiter Dobrev
In Reinforcement Learning we assume that a model of the world exists. We assume that this model is perfect (that is, it describes the world completely and unambiguously). In this article we will show that it makes no sense to look for the perfect model, because this model is too complex and practically cannot be found. We will show that we must forget about perfection and look for event-driven models instead. These models are a generalization of the Markov decision process (MDP) models. This generalization is very important, because without it nothing can be found. Instead of one perfect MDP model, we will be looking for a large number of simple event-driven models, each of which describes some simple dependency or property. That is, we will replace the search for one complicated perfect model with the search for a large number of simple models.
Comments: 32 Pages. Bulgarian language
Unique-IP document downloads: 11 times
Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.
Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.