The AI Definition and a Program Which Satisfies this Definition

TL;DR

This paper defines AI as a computable policy close to the optimal, introduces a language for describing the world, and develops a theoretical program that understands and predicts the environment, with potential for future improvements.

Contribution

It formalizes an AI definition based on proximity to the best policy and constructs a theoretical program satisfying this definition using a new world description language.

Findings

Existence of a best performing policy among all policies

A computable policy can approximate the best policy

A conceptual program can understand and predict the environment

Abstract

We will consider all policies of the agent and will prove that one of them is the best performing policy. While that policy is not computable, computable policies do exist in its proximity. We will define AI as a computable policy which is sufficiently proximal to the best performing policy. Before we can define the agent's best performing policy, we need a language for description of the world. We will also use this language to develop a program which satisfies the AI definition. The program will first understand the world by describing it in the selected language. The program will then use the description in order to predict the future and select the best possible move. While this program is extremely inefficient and practically unusable, it can be improved by refining both the language for description of the world and the algorithm used to predict the future. This can yield a program which is both efficient and consistent with the AI definition.