Interactive Learning of Expert Criteria for Rescue Simulations

The goal of our work is to build a DSS (Decision Support System) to support resource allocation and planning for natural disaster emergencies in urban areas such as Hanoi in Vietnam. The first step has been to conceive a multi-agent environment that supports simulation of disasters, taking into account geospatial, temporal and rescue organizational information. The problem we address is the acquisition of situated expert knowledge that is used to organize rescue missions. We propose an approach based on participatory techniques, interactive learning and machine learning. This paper presents an algorithm that incrementally builds a model of the expert knowledge by online analysis of its interaction with the simulator's proposed scenario.

[1]  Brahim Chaib-draa,et al.  Comparison of different coordination strategies for the RoboCupRescue simulation , 2004 .

[2]  Brahim Chaib-draa,et al.  Multiagent Systems Viewed as Distributed Scheduling Systems: Methodology and Experiments , 2005, Canadian Conference on AI.

[3]  C. Nieuwenhuis.  Agent-Based Disaster Simulation Evaluation and its Probability Model Interpretation , 2007 .

[4]  François Sempé,et al.  An artificial maieutic approach for eliciting experts' knowledge in multi-agent simulations , 2005, AAMAS '05.

[5]  Alexis Drogoul,et al.  An Artificial Maieutic Approach for Eliciting Experts' Knowledge in Multi-agent Simulations , 2005, MABS.

[6]  Sébastien Paquet.  Learning Coordination in RoboCupRescue , 2003, Canadian Conference on AI.

[7]  Jon Eisenberg,et al.  Improving Disaster Management: The Role of IT in Mitigation, Preparedness, Response, and Recovery , 2007 .

[8]  Brahim Chaib-draa,et al.  Real-Time Decision Making for Large POMDPs , 2005, Canadian Conference on AI.

[9]  Frank Fiedrich,et al.  An HLA-Based Multiagent System for Optimized Resource Allocation After Strong Earthquakes , 2006, Proceedings of the 2006 Winter Simulation Conference.

[10]  Alexis Drogoul,et al.  Using Computational Agents to Design Participatory Social Simulations , 2007, J. Artif. Soc. Soc. Simul..

[11]  Silvia Suárez,et al.  Co-operation strategies for strengthening civil agents ’ lives in the RoboCup-Rescue simulator scenario , 2003 .

[12]  Gabriel A. Wainer,et al.  Proceedings of the 2016 Winter Simulation Conference , 2016 .

[13]  Alexis Drogoul,et al.  GAMA: An Environment for Implementing and Running Spatially Explicit Multi-agent Simulations , 2009, PRIMA.

[14]  Brahim Chaib-draa,et al.  Multi-attribute Decision Making in a Complex Multiagent Environment Using Reinforcement Learning with Selective Perception , 2004, Canadian Conference on AI.

[15]  Jaime Simão Sichman,et al.  Multi-Agent-Based Simulation VI , 2005, Lecture Notes in Computer Science.

[16]  Milind Tambe,et al.  Agent-Based Simulations for Disaster Rescue Using the DEFACTO Coordination System , 2005, Emergent Information Technologies and Enabling Policies for Counter-Terrorism.

[17]  Linet Özdamar,et al.  Greedy Neighborhood Search for Disaster Relief and Evacuation Logistics , 2008, IEEE Intelligent Systems.

[18]  Minh Nguyen-Duc,et al.  Vers la conception participative de simulations sociales : application à la gestion du trafic aérien , 2005 .

[19]  Brahim Chaib-draa,et al.  Comparison of Different Coordination Strategies for the RoboCupRescue Simulation , 2004, IEA/AIE.

[20]  Moonis Ali,et al.  Innovations in Applied Artificial Intelligence , 2005 .

[21]  Brahim Chaib-draa,et al.  An online POMDP algorithm for complex multiagent environments , 2005, AAMAS '05.

[22]  Andrew McCallum,et al.  Reinforcement learning with selective perception and hidden state , 1996 .

[23]  Moshe Tennenholtz,et al.  Artificial Social Systems , 1992, Lecture Notes in Computer Science.

[24]  Sébastien Paquet,et al.  Distributed Decision-Making and TaskCoordination in Dynamic, Uncertain andReal-Time Multiagent Environments , 2005 .

[25]  Daniele Nardi,et al.  Using the RoboCup-Rescue Simulator in an Italian Earthquake Scenario. , 2003 .

[26]  A. Drogoul,et al.  Multi-Agent Simulation as a Tool for Modeling Societies: Application to Social Differentiation in Ant Colonies , 1992, MAAMAW.