Analysis of Algorithms and Partial Algorithms

01/13/2016
by   Andrew MacFie, et al.
0

We present an alternative methodology for the analysis of algorithms, based on the concept of expected discounted reward. This methodology naturally handles algorithms that do not always terminate, so it can (theoretically) be used with partial algorithms for undecidable problems, such as those found in artificial general intelligence (AGI) and automated theorem proving. We mention an approach to self-improving AGI enabled by this methodology. Aug 2017 addendum: This article was originally written with multiple audiences in mind. It is really best put in the following terms. Goertzel, Hutter, Legg, and others have developed a definition of an intelligence score for a general abstract agent: expected lifetime reward in a random environment. AIXI is generally the optimal agent according to this score, but there may be reasons to analyze other agents and compare score values. If we want to use this definition of intelligence in practice, perhaps we can start by analyzing some simple agents. Common algorithms can be thought of as simple agents (environment is input, reward is based on running time) so we take the goal of applying the agent intelligence score to algorithms. That is, we want to find, what are the IQ scores of algorithms? We can do some very simple analysis, but the real answer is that even for simple algorithms, the intelligence score is too difficult to work with in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/06/2021

Reward-Punishment Symmetric Universal Intelligence

Can an agent's intelligence level be negative? We extend the Legg-Hutter...
research
10/22/2019

Intelligence via ultrafilters: structural properties of some intelligence comparators of deterministic Legg-Hutter agents

Legg and Hutter, as well as subsequent authors, considered intelligent a...
research
05/21/2022

Computable Artificial General Intelligence

An artificial general intelligence (AGI), by one definition, is an agent...
research
08/27/2014

Definition and properties to assess multi-agent environments as social intelligence tests

Social intelligence in natural and artificial systems is usually measure...
research
08/03/2013

Universal Empathy and Ethical Bias for Artificial General Intelligence

Rational agents are usually built to maximize rewards. However, AGI agen...
research
10/15/2019

How a minimal learning agent can infer the existence of unobserved variables in a complex environment

According to a mainstream position in contemporary cognitive science and...
research
10/06/2021

Reconsidering Optimistic Algorithms for Relational DBMS

At DBKDA 2019, we demonstrated that StrongDBMS with simple but rigorous ...

Please sign up or login with your details

Forgot password? Click here to reset