Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
Local search techniques have attracted considerable interest in the Artificial Intelligence (AI) community since the development of GSAT [9] and the min-conflicts heuristic [5] ...
John Thornton, Matthew Beaumont, Abdul Sattar, Mic...
This paper addresses the problem of solving conflicts in railway traffic that arise due to disturbances. It is formulated as a problem of re-scheduling meets and overtakes of trai...
We show how the concave-convex procedure can be applied to transductive SVMs, which traditionally require solving a combinatorial search problem. This provides for the first time ...
Ronan Collobert, Fabian H. Sinz, Jason Weston, L&e...
Multiobjective evolutionary algorithms (MOEA) are an effective tool for solving search and optimization problems containing several incommensurable and possibly conflicting objec...