Module-Based Reinforcement Learning: Experiments with a Real Robot
Machine Learning - Special issue on learning in autonomous robots
Learning classifier systems: a complete introduction, review, and roadmap
Journal of Artificial Evolution and Applications
Module-Based Reinforcement Learning: Experiments with a Real Robot
Autonomous Robots
RTCS: a Reactive with Tags Classifier System
Journal of Intelligent and Robotic Systems
Journal of Intelligent and Robotic Systems
What Is a Learning Classifier System?
Learning Classifier Systems, From Foundations to Applications
A Learning Classifier Systems Bibliography
Learning Classifier Systems, From Foundations to Applications
A Roadmap to the Last Decade of Learning Classifier System Research
Learning Classifier Systems, From Foundations to Applications
A Bigger Learning Classifier Systems Bibliography
IWLCS '00 Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems
Recent trends in learning classifier systems research
Advances in evolutionary computing
Evolutionary approaches to fuzzy modelling for classification
The Knowledge Engineering Review
Improving XCS Performance by Distribution
SEAL '08 Proceedings of the 7th International Conference on Simulated Evolution and Learning
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Learning classifier systems: a complete introduction, review, and roadmap
Journal of Artificial Evolution and Applications
Speedup character-based matching in learning classifier systems with Xor
Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
ICAISC'10 Proceedings of the 10th international conference on Artificial intelligence and soft computing: Part I
| Hi-index | 0.00 |
In this article we investigate the feasibility of using learning classifier systems as a tool for building adaptive control systems for real robots. Their use on real robots imposes efficiency constraints which are addressed by three main tools: parallelism, distributed architecture, and training. Parallelism is useful to speed up computation and to increase the flexibility of the learning system design. Distributed architecture helps in making it possible to decompose the overall task into a set of simpler learning tasks. Finally, training provides guidance to the system while learning, shortening the number of cycles required to learn. These tools and the issues they raise are first studied in simulation, and then the experience gained with simulations is used to implement the learning system on the real robot. Results have shown that with this approach it is possible to let the AutonoMouse, a small real robot, learn to approach a light source under a number of different noise and lesion conditions.