1410 search results - page 166 / 282 » The Algorithmics of Solitaire-Like Games |
SEAL
1998
Springer
15 years 4 months ago
1998
Springer
Abstract. Robustness has long been recognised as a critical issue for coevolutionary learning. It has been achieved in a number of cases, though usually in domains which involve so...
COCO
2008
Springer
15 years 1 months ago
2008
Springer
We study the approximability of predicates on k variables from a domain [q], and give a new sufficient condition for such predicates to be approximation resistant under the Unique...
ATAL
2010
Springer
15 years 26 days ago
2010
Springer
We investigate planning for self-interested agents in large multi-agent simulations. We present two heuristic algorithms that exploit different domain-specific properties in order...
ICML
2010
IEEE
15 years 25 days ago
2010
IEEE
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality agains...
PRL
2008
14 years 11 months ago
2008
We consider an active learning game within a transductive learning model. A major problem with many active learning algorithms is that an unreliable current hypothesis can mislead...