Abstract
Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence.
Original language | English |
---|---|
Title of host publication | 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings |
DOIs | |
Publication status | Published - 2013 |
Event | 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, Japan Duration: Aug 18 2013 → Aug 22 2013 |
Other
Other | 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 |
---|---|
Country/Territory | Japan |
City | Osaka |
Period | 8/18/13 → 8/22/13 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Human-Computer Interaction
- Software