Planning as search: a quantitative approach
Artificial Intelligence
Learning to Perceive and Act by Trial and Error
Machine Learning
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Temporal difference learning and TD-Gammon
Communications of the ACM
Using temporal logic to control search in a forward chaining planner
New directions in AI planning
Fast planning through planning graph analysis
Artificial Intelligence
Genetic programming: an introduction: on the automatic evolution of computer programs and its applications
Toward a Model of Intelligence as an Economy of Agents
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
A Critical Review of Classifier Systems
Proceedings of the 3rd International Conference on Genetic Algorithms
Relational Reinforcement Learning
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Implementing Semantic Network Structures Using the Classifier System
Proceedings of the 1st International Conference on Genetic Algorithms
Finding optimal solutions to Rubik's cube using pattern databases
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
CONTEXT '01 Proceedings of the Third International and Interdisciplinary Conference on Modeling and Using Context
An Artificial Economy of Post Production Systems
IWLCS '00 Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems
A Working Hypothesis for General Intelligence
Proceedings of the 2007 conference on Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms: Proceedings of the AGI Workshop 2006
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
| Hi-index | 0.00 |
We address the problem of how to reinforce learning in ultracomplex environments, with huge state-spaces, where one must learn to exploit a compact structure of the problem domain. The approach we propose is to simulate the evolution of an artificial economy of computer programs. The economy is constructed based on two simple principles so as to assign credit to the individual programs for collaborating on problem solutions. We find empirically that starting from programs that are random computer code, we can develop systems that solve hard problems. In particular, our economy learned to solve almost all random Blocks World problems with goal stacks that are 200 blocks high. Competing methods solve such problems only up to goal stacks of at most 8 blocks. Our economy has also learned to unscramble about half a randomly scrambled Rubik's cube and to solve several commercially sold puzzles.