Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Behavior-based artificial intelligence
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Inductive functional programming using incremental program transformation
Artificial Intelligence
Evaluation and Selection of Biases in Machine Learning
Machine Learning - Special issue on bias evaluation and selection
Recombination, selection, and the genetic construction of computer programs
Recombination, selection, and the genetic construction of computer programs
Predicate Invention in ILP - an Overview
ECML '93 Proceedings of the European Conference on Machine Learning
Causality in Genetic Programming
Proceedings of the 6th International Conference on Genetic Algorithms
An analysis of genetic programming
An analysis of genetic programming
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
| Hi-index | 0.00 |
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive generalization over a very large set of situations. Second they facilitate modularization. In this paper we compare several randomized algorithms for learning modular procedural representations. The main algorithm, called Adaptive Representation through Learning (ARL) is a genetic programming extension that relies on the discovery of subroutines. ARL is suitable for learning hierarchies of subroutines and for constructing policies to complex tasks. ARL was successfully tested on a typical reinforcement learning problem of controlling an agent in a dynamic and nondeterministic environment where the discovered subroutines correspond to agent behaviors.