
Algorithmic learning of probability distributions from random data in the limit
We study the problem of identifying a probability distribution for some ...
read it

An effective version of definability in metric model theory
In this paper, a computably definable predicate is defined and character...
read it

A Galois connection between Turing jumps and limits
Limit computable functions can be characterized by Turing jumps on the i...
read it

The normalized algorithmic information distance can not be approximated
It is known that the normalized algorithmic information distance N is no...
read it

On Computability of Data Word Functions Defined by Transducers
In this paper, we investigate the problem of synthesizing computable fun...
read it

Learning Qnetwork for Active Information Acquisition
In this paper, we propose a novel Reinforcement Learning approach for so...
read it

New PotentialBased Bounds for the GeometricStopping Version of Prediction with Expert Advice
This work addresses the classic machine learning problem of online predi...
read it
On the Computability of AIXI
How could we solve the machine learning and the artificial intelligence problem if we had infinite computation? Solomonoff induction and the reinforcement learning agent AIXI are proposed answers to this question. Both are known to be incomputable. In this paper, we quantify this using the arithmetical hierarchy, and prove upper and corresponding lower bounds for incomputability. We show that AIXI is not limit computable, thus it cannot be approximated using finite computation. Our main result is a limitcomputable ϵoptimal version of AIXI with infinite horizon that maximizes expected rewards.
READ FULL TEXT
Comments
There are no comments yet.