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...
Chris Gaskett, David Wettergreen, Alexander Zelins...
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...
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),...