Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
An integrated solution to guarantee real-time requirements in embedded real-time monitor and control systems is presented in this paper. First l task model is abstracted from such ...
This document presents provisioning strategies for emerging hybrid optical networks. The idea is to make use of policy-based management that guides the behavior of a network throu...
Agents are an emerging technology that grants programmers a new way to exploit distributed resources. Roles are a powerful concept that can be used to model agent interactions, all...
In this paper we are concerned with the problem of learning how to solve planning problems in one domain given a number of solved instances. This problem is formulated as the probl...