A common goal in Reinforcement Learning is to derive a good strategy given a limited batch of data. In this paper, we adopt the safe policy improvement (SPI) approach: we compute a target policy guaranteed to perform at least as well as a given baseline policy. Our SPI strategy, inspired by the knows-what-it-knows paradigms, consists in bootstrapping the target policy with the baseline policy w...

The aim of this work is to produce and test a robust, distributed, multi-agent task allocation algorithm, as these are scarce and not well-documented in the literature. The vehicle used to create the robust system is the Performance Impact algorithm (PI), as it has previously shown good performance. Three different variants of PI are designed to improve its robustness, each using Monte Carlo sa...

Existing traditional and ConvNet-based methods for light field depth estimation mainly work on the narrow-baseline scenario. This paper explores feasibility capability of ConvNets to estimate in another promising scenario: wide-baseline fields. Due deficiency training samples, a large-scale diverse synthetic dataset with labelled data is introduced prediction tasks. Considering practical goal r...

Achieving better understanding phosphorus (P) flows through urban ecosystems is needed to conserve P, as non-renewable phosphate rock deposits become depleted and the global human population increases. A baseline mass flow analysis (MFA) for P developed for the Twin Cities Watershed (TCW, which includes most of the Minneapolis-St. Paul metropolitan region) showed that most P input was stored in...

The KLuB project is an attempt to use formal methods in the process and product of requirements engineering of information systems. In the work presented here, the scenario technique was used for requirements elicitation. Scenarios, which have been recognized as an effective technique for eliciting requirements, focus usually on behavior and less on data. An additional objective of the project ...

In this article we show the results of an extensive research on scenario evolution. We investigated twelve case studies spanning over 200 scenarios that contained over 800 episodes. The research aimed at capturing data on scenario evolution in order to confirm previous results and to elicitate the requirements for a scenario evolution support environment. Our findings are organised in a three t...

The KLuB project is an attempt to use formal methods in the process and product of requirements engineering of information systems. In the work presented here, the scenario technique was used for requirements elicitation. Scenarios, which have been recognized as an effective technique for eliciting requirements, focus usually on behavior and less on data. An additional objective of the project ...

With the emergence of Web 2.0, people are able to share their thoughts and photos with their friends and strangers. Yet, they also risk invasion of their privacy. Information privacy has therefore become an important issue in the information age. In this research, we focus on the influence of anger on immoral judgment of privacy invasion in cyberspace. Specifically, two scenarios, nonviolent an...

This paper assumes each user has more than one queue, derives a new packet-dependant proportional fairness power allocation pattern based on the sum of weight capacity and the packet’s priority in users’ queues, and proposes 4 new cross-layer packet-dependant OFDM scheduling schemes based on proportional fairness for heterogeneous classes of traffic. Scenario 1, scenario 2 and scenario 3 lead r...

We consider the problem of designing a pricing mechanism for precisely controlling the real-time balance in electricity markets, where retail brokers aggregate the supply and demand of a number of individual customers, and must purchase or sell power at the wholesale level such that the total supply matches total demand. This is typically done for future time periods by buying and selling power...