Search results for "Decision process"
showing 10 items of 52 documents
Designing a multi-layer edge-computing platform for energy-efficient and delay-aware offloading in vehicular networks
2021
Abstract Vehicular networks are expected to support many time-critical services requiring huge amounts of computation resources with very low delay. However, such requirements may not be fully met by vehicle on-board devices due to their limited processing and storage capabilities. The solution provided by 5G is the application of the Multi-Access Edge Computing (MEC) paradigm, which represents a low-latency alternative to remote clouds. Accordingly, we envision a multi-layer job-offloading scheme based on three levels, i.e., the Vehicular Domain, the MEC Domain and Backhaul Network Domain. In such a view, jobs can be offloaded from the Vehicular Domain to the MEC Domain, and even further o…
Least-squares temporal difference learning based on an extreme learning machine
2014
Abstract Reinforcement learning (RL) is a general class of algorithms for solving decision-making problems, which are usually modeled using the Markov decision process (MDP) framework. RL can find exact solutions only when the MDP state space is discrete and small enough. Due to the fact that many real-world problems are described by continuous variables, approximation is essential in practical applications of RL. This paper is focused on learning the value function of a fixed policy in continuous MPDs. This is an important subproblem of several RL algorithms. We propose a least-squares temporal difference (LSTD) algorithm based on the extreme learning machine. LSTD is typically combined wi…
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
2018
Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms that prevent them from converging towards the global optima. It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms. Games are often used to benchmark reinforcement learning algorithms as they provide a flexible, reproducible, and easy to control environment. Regardless, few games feature a state-space where results in exploration, memory, and plannin…
Supporting public decision process in buildings energy retrofitting operations: the application of a Multiple Criteria Decision Aiding model to a cas…
2020
Abstract The challenge of promoting sustainable cities and reaching the objectives developed by the European Green Deal includes the renovation of the building sector, as it is responsible for 40% of energy consumption in Europe. Regional or local public administrations have to allocate their financial resources for improving the energy performances of their building stock and to face a multidimensional problem, where different aspects – such as energy efficiency, financial-economic feasibility and environmental protection – have to be harmonized. The present study proposes a Multiple Criteria Decision Aiding model, which includes the ELECTRE TRI-nC method, for supporting the public decisio…
Integrated Production and Predictive Maintenance Planning based on Prognostic Information
2019
International audience; This paper address the problem of scheduling production and maintenance operation in predictive maintenance context. It proposes a contribution in the decision making phase of the prognostic and health management framework. Theprognostics and decision processes are merged and an ant colony optimization approach for finding the sequence of decisions that optimizes the benefits of a production system is developed. A case study on a single machine composed of several components where machine can have several usage profiles. The results show thatour approach surpasses classical condition based maintenance policy.
Sequence Q-learning: A memory-based method towards solving POMDP
2015
Partially observable Markov decision process (POMDP) models a control problem, where states are only partially observable by an agent. The two main approaches to solve such tasks are these of value function and direct search in policy space. This paper introduces the Sequence Q-learning method which extends the well known Q-learning algorithm towards the ability to solve POMDPs through adding a special sequence management framework by advancing from action values to “sequence” values and including the “sequence continuity principle”.
The Rail Quality Index as an Indicator of the “Global Comfort” in Optimizing Safety, Quality and Efficiency in Railway Rails
2012
AbstractThe proposed model uses the stochastic dynamic programming and in particular Markov decision processes applied to the Rail Quality Index (RQI - Italian Indice di Qualità del Binario, IQB).By performing the integrated analysis of the classes of variables which characterize the overall service quality (in terms of comfort and safety), the proposed mathematical approach allows to find the solutions to the decision-making process in function of the probability of deterioration of the state variables of the infrastructure over time and of the flow of available resources.
Inside the robot’s mind during human-robot interaction
2019
Humans and robots collaborating and cooperating for pursuing a shared objective need to rely on the other for carrying out an effective decision process and for updating knowledge when necessary in a dynamic environment. Robots have to behave as they were human teammates. To model the cognitive process of robots during the interaction, we developed a cognitive architecture that we implemented employing the BDI (belief, desire, intention) agent paradigm. In this paper, we focus on how to let the robot show to the human its reasoning process and how its knowledge on the work environment grows. We realized a framework whose heart is a simulator that serves the human as a window on the robot’s …
Decision Process in Human-Agent Interaction: Extending Jason Reasoning Cycle
2019
The main characteristic of an agent is acting on behalf of humans. Then, agents are employed as modeling paradigms for complex systems and their implementation. Today we are witnessing a growing increase in systems complexity, mainly when the presence of human beings and their interactions with the system introduces a dynamic variable not easily manageable during design phases. Design and implementation of this type of systems highlight the problem of making the system able to decide in autonomy. In this work we propose an implementation, based on Jason, of a cognitive architecture whose modules allow structuring the decision-making process by the internal states of the agents, thus combini…
A Cognitive Dialogue Manager for Education Purposes
2011
A conversational agent is a software system that is able to interact with users in a natural way, and often uses natural language capabilities. In this chapter, an evolution of a conversational agent is presented according to the definition of dialogue management techniques for the conversational agents. The presented conversational agent is intended to act as a part of an educational system. The chapter outlines the state-of-the-art systems and techniques for dialogue management in cognitive educational systems, and the underlying psychological and social aspects. We present our framework for a dialogue manager aimed to reduce the uncertainty in users’ sentences during the assessment of hi…