Authors: Dimiter Dobrev
In Reinforcement Learning we are looking for meaning in the stream of input-output information. If we do not find sense, this stream will be just a noise for us. To find meaning, we must learn to discover and recognize objects. What is an object? In this article we will show that the object is an event-driven model. These models are a generalization of action-driven models. In the Markov decision process we have an action-driven model and there the states are changing at each step. The advantage of event-driven models is that they are more stable and change their state only when certain events occur. These events can happen very rarely, so the current state of the event-driven model is much more predictable.
Comments: 26 Pages. Bulgarian language
[v1] 2018-11-05 08:30:13
Unique-IP document downloads: 14 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.