| Creators: |
Faußer, Stefan A. and Schwenker, Friedhelm |
| Title: |
Neural Approximation of Monte CarloPolicy Evaluation Deployed in Connect Four |
| Item Type: |
Conference or Workshop Item |
| Event Title: |
(Proceedings of the) 3rd IAPR Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR) |
| Event Location: |
Paris, France |
| Event Dates: |
July, 2-4, 2008 |
| Page Range: |
pp. 90-100 |
| Date: |
2008 |
| Divisions: |
Informationsmanagement |
| Abstract (ENG): |
To win a board-game or more generally to gain something specific in a given Markov-environment, it is most important to have a policy in choosing and taking actions that leads to one of several qualitative good states. In this paper we describe a novel method to learn a game-winning strategy. The method predicts statistical probabilities to win in given game states using a state-value function that is approximated by a Multi-layer perceptron. Those predictions will improve according to rewards given in terminal states. We have deployed that method in the game Connect Four and have compared its game-performance with Velena [5]. |
| Forthcoming: |
No |
| Language: |
English |
| Citation: |
Faußer, Stefan A. and Schwenker, Friedhelm
(2008)
Neural Approximation of Monte CarloPolicy Evaluation Deployed in Connect Four.
In: (Proceedings of the) 3rd IAPR Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), July, 2-4, 2008, Paris, France, pp. 90-100.
ISBN 9783540699385
|
 |
View Item in edit mode (academic staff only) |
