Program Search as a Path to Artificial General Intelligence

  title={Program Search as a Path to Artificial General Intelligence},
  author={Lukasz Kaiser},
  booktitle={Artificial General Intelligence},
  • Lukasz Kaiser
  • Published in
    Artificial General…
  • Computer Science
It is difficult to develop an adequate mathematical definition of intelligence. Therefore we consider the general problem of searching for programs with specified properties and we argue, using the Church-Turing thesis, that it covers the informal meaning of intelligence. The program search algorithm can also be used to optimise its own structure and learn in this way. Thus, developing a practical program search algorithm is a way to create AI. 
The EU and artificial intelligence: A human-centred perspective
This article analyses the potential benefits and drawbacks of artificial intelligence (AI). It argues that the EU should become a leading force in AI development. As a goal that captures the public
The special issue of the Vladimir State University named after Alexander and Nikolay Stoletovs based on results of the 20th International Conference on Physics of Light-Matter Coupling in


Optimal Ordered Problem Solver
An efficient, recursive, backtracking-based way of implementing OOPS on realistic computers with limited storage is introduced, and experiments illustrate how OOPS can greatly profit from metalearning or metasearching, that is, searching for faster search procedures.
The use of training sequences of problems for machine knowledge acquisition promises to yield Expert Systems that will be easier to train and free of the brittleness that characterizes the narrow specialization of present day systems of this sort.
A Theory of Universal Artificial Intelligence based on Algorithmic Complexity
This work constructs a modified algorithm AI tl, which is still eectively more intelligent than any other time t and space l bounded agent, and gives strong arguments that the resulting AI model is the most intelligent unbiased agent possible.
Term rewriting and all that
Term Rewriting and All That is a self-contained introduction to the field of term rewriting and covers all the basic material including abstract reduction systems, termination, confluence, completion, and combination problems.
Gödel Machines: Fully Self-referential Optimal Universal Self-improvers
The first class of mathematically rigorous, general, fully self-referential, self-improving, optimally efficient problem solvers is presented, which not only boasts an optimal order of complexity but can optimally reduce any slowdowns hidden by the O()-notation, provided the utility of such speed-ups is provable at all.
Listlessness is better than laziness: Lazy evaluation and garbage collection at compile-time
One reason for interest in functional programming is that it is well-suited for program development by transformation: begin by writing a clear (but inefficient) program, and transform this to an
The New AI: General & Sound & Relevant for Physics
The new millennium has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference based on Occam's razor, problem solving, decision making, and reinforcement learning in environments of a very general type.
Formal verification of probabilistic algorithms
  • J. Hurd
  • Computer Science, Mathematics
  • 2003
This thesis shows how probabilistic algorithms can be formally verified using a mechanical theorem prover, and defines a version with strong properties, which can execute in the logic to prove compositeness of numbers.
Universal Artificial Intellegence - Sequential Decisions Based on Algorithmic Probability
  • Marcus Hutter
  • Education
    Texts in Theoretical Computer Science. An EATCS Series
  • 2005
Reading a book as this universal artificial intelligence sequential decisions based on algorithmic probability and other references can enrich your life quality.