Erwan Tranvouez

An organization-oriented methodological framework for agent-based supply chain simulation

The SC organizational structure, and related management policies, is a crucial factor that can be adjusted to improve the SC performance, which consequently has to be taken into account in the SC modeling and simulation. This paper addresses a new methodological framework in the context of an agent-based SC simulation, which permits modeling and simulation of such SC organizational aspects, allowing observables of different levels of details. This methodological framework is structured according to two main abstraction levels, a conceptual level and an operational level. For each of these levels, different models are proposed and presented in detail. This methodological framework is associated with a multi model and multi-paradigm software architecture adapted to the SC simulation.

Improving Players’ Assessment in Crisis Management Serious Games: The SIMFOR Project

Serious Games (SG) are more and more used for training in various domains, but notably in crisis management. In order to improve training results, learner assessment can provide insights on what went right or wrong during a training session. Such assessment is more complex when actors’ individual actions must be considered, but also the results of their interactions (collective actions). Such interactions can either be engaged with real or simulated players, through adaptive dialogues immersing players in the different ways (actions, procedures, …) to manage a crisis. This paper presents a multi-agent simulation and assessment approach of SG players, targeting the management of distributed and heterogeneous information (in nature or source) based on the concept of Evaluation Space allowing the production of individual and collective assessments. This approach is developed and illustrated on the SIMFOR SG dedicated to crisis management.

Intelligent Tutoring Systems and Serious Game for Crisis Management: A Multi-agents Integration Architecture

Crisis management, serious games (SG) are more and more used for training. SG permit to reduce the cost of a such training and saving time, and in general provide a fun way to learn. In this paper we propose to bring together SG and Intelligent Tutoring Systems (ITS) in the context of the SIMFOR project, a SG for training in crisis management. We discuss the problems and needs of serious games and an overview of existing works. To enhance the learning aspect in SG, we propose the integration of different ITS functionalities to the SG. To perform this integration process, we propose an collaborative agent-based architecture. This architecture is presented in detail and illustrated on a realistic game scenario.

A Multi-Agent Based Scheduling System: A Co-Operative and Reactive Approach

Abstract This paper presents a co-operative and reactive model and a multiagent architecture for co-operative scheduling in a jobshop context. First we introduce a workshop scheduling model structured according to three decision levels enabling. through co-operation. to absorb disruptions internal to a production cell composed of autonomous machines. Next we present a multi-agent system currently in development. simulating the reactive and co-operative scheduling of a production cell according to the preceding model. Then. agents and different co-operation protocols allowing them to solve an internal perturbation are described. Finally. we conclude on the limits and the perspectives of our research.

Learners’ Assessment and Evaluation in Serious Games: Approaches and Techniques Review

Recently, there has been growing interest in the use of Serious Games (SG), as they provide a more powerful means of knowledge transfer in almost every application domain especially in the crisis management field. With this increasing adoption of SG, designing novel techniques for learners’ assessment and evaluation has become of paramount importance to improve learning results and thus to maintain players’ motivation. This paper focuses on the learners’ assessment and evaluation in SG. After defining assessment and evaluation, we distinguish two main approaches: implicit and explicit. For each of these approaches, we present some techniques currently used in some existing games. Then we compare these different approaches and techniques. This synthesis is expected to help researchers and games creators working in this area and identifying benefits and limitations of these techniques in order to develop a new comprehensive technique that outperforms all existing ones.

A MultiAgent Architecture for Collaborative Serious Game applied to Crisis Management Training: Improving Adaptability of Non Player Characters

Serious Games (SG) are more and more used for training, as in the crisis management domain, where several hundred stakeholders can be involved, causing various organizational difficulties on field exercises. SGs specific benefits include player immersion and detailed players’ actions tracking during a virtual exercise. Moreover, Non Player Characters (NPC) can adapt the crisis management exercise perimeter to the available stakeholders or to specific training objectives. In this paper we present a Multi-Agent System architecture supporting behavioural simulation as well as monitoring and assessment of human players. A NPC is enacted by a Game Agent which reproduces the behaviour of a human actor, based on a deliberative model (Belief Desire Intention). To facilitate the scenario design, an Agent editor allows a designer to configure agents’ behaviours. The behaviour simulation was implemented within the pre-existing SIMFOR project, a serious game for training in crisis management. Received on 30 December 2013; accepted on 31 March 2014; published on 22 May 2014