9 search results - page 1 / 2 » ausai 1999 |
AUSAI
1999
Springer
13 years 10 months ago
1999
Springer
AUSAI
1999
Springer
13 years 10 months ago
1999
Springer
AUSAI
1999
Springer
13 years 10 months ago
1999
Springer
Abstract. Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Qlearning is commonly applied to problems with d...
AUSAI
1999
Springer
13 years 10 months ago
1999
Springer
This paper analyzes the notion of a minimal belief change that incorporates new information. I apply the fundamental decisiontheoretic principle of Pareto-optimality to derive a no...
AUSAI
1999
Springer
13 years 10 months ago
1999
Springer
In previous work solutions for the nesting problem are produced using the no fit polygon (NFP), a new evaluation method and three evolutionary algorithms (simulated annealing (SA),...