Universal Induction with Varying Sets of Combinators
This addresses the challenge of adaptive reference machines for AGI, but it is incremental as it builds on existing combinatory logic and genetic programming approaches.
The paper tackled the problem of universal induction in AGI by using combinatory logic as a reference machine with varying sets of primitive combinators, and experiments showed that low-complexity tasks could be solved more efficiently than brute force, with useful combinators simplifying harder tasks.
Universal induction is a crucial issue in AGI. Its practical applicability can be achieved by the choice of the reference machine or representation of algorithms agreed with the environment. This machine should be updatable for solving subsequent tasks more efficiently. We study this problem on an example of combinatory logic as the very simple Turing-complete reference machine, which enables modifying program representations by introducing different sets of primitive combinators. Genetic programming system is used to search for combinator expressions, which are easily decomposed into sub-expressions being recombined in crossover. Our experiments show that low-complexity induction or prediction tasks can be solved by the developed system (much more efficiently than using brute force); useful combinators can be revealed and included into the representation simplifying more difficult tasks. However, optimal sets of combinators depend on the specific task, so the reference machine should be adaptively chosen in coordination with the search engine.