MDS (Monitoring and Discovery Service) is a key infrastructure in grid computing, it mainly undertake registry, updating and discovery of all sorts of resource information in the grid environment. The information organized and released by the MDS is the descriptive information of diversified resources (net resources, computing resources, data resources etc), including data, services and entitie...

This paper addresses the problem of knowledge transfer in lifelong reinforcement learning. It proposes an algorithm which learns policy constraints, i.e., rules that characterize action selection in entire families of reinforcement learning tasks. Once learned, policy constraints are used to bias learning in future, similar reinforcement learning tasks. The appropriateness of the algorithm is d...

the geographic distribution of astragalus l. (fabaceae) was analyzed using a database of 12377 geo-referenced observations. in the old world (including asia, africa and europe) there are ca. 2900 euploid species classified in 166 distinct sections. in this study using geographic information system (gis) by means of diva-gis (ver. 4) distribution map of some more important sections in the old wo...

the pull- out strength of the reinforcement has a significant role on the function of the most reinforced soil structures. since the coarse grain soils have a better interaction with the reinforcement, they are mostly used in these structures. in most situations, we have to transfer these granular soils from the borrow area, usually far from the site of the project. this will impose a considera...

With this paper we describe a well suited, scalable problem for reinforcement learning approaches in the field of mobile robots. We show a suitable representation of the problem for a reinforcement approach and present our results with a model based standard algorithm. Two different approximators for the value function are used, a grid based approximator and a neural network based approximator.