Gradient-based approaches to direct policy search in reinforcement learning have received much recent attention as a means to solve problems of partial observability and to avoid some of the problems associated with policy degradation in value-function methods. In this paper we introduce GPOMDP,...

Previous research has suggested that depth of search in chess does not increase much as a function of skill. We submitted players to a problem-solving task with complex positions. We found a strong skill effect in depth of search, rate of search, and number of nodes generated. At the level of...

This paper develops a cell-based formulation for the simultaneous route and departure time choice problem with elastic demands through a variational inequality problem (VIP). This formulation follows the ideal Dynamic User Optimal (DUO) route and departure time choice principle and encapsulates...

This qualitative research explores the problem-solving process of public schoolprincipals. Drawing on in-depth interviews with successful principals, three distinctelements influencing the process were discovered. First, principals often engage in apractice the author identifies as policy...

Problem-based learning (PBL) is an instructional model that assumes the centrality of problems to learning. Research on PBL has focused on student learning, student roles, tutor roles, problem design, and technology use (Hung, Jonassen, & Liu, 2008), but little attention in the PBL literature...

Abstract The creation of knowledge, the advanced research in strategic directions, the increasing of economic competitiveness and the transfer of knowledge in the economy are priorities of economic policies. They are based on research, development and innovation activities, which although take...