Fuzzy and tile coding approximation techniques for coevolution in reinforcement learning
This thesis investigates reinforcement learning algorithms suitable for learning in large state space problems and coevolution. In order to learn in large state spaces, the state space must be collapsed to a computationally feasible size and then generalised about. This thesis presents two new imple...
| Main Author: | |
|---|---|
| Published: |
Queen Mary, University of London
2005
|
| Subjects: | |
| Online Access: | https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.423157 |