Vincent Corruble

AAMAS Conference 2023 Conference Paper

Multi-objective Reinforcement Learning in Factored MDPs with Graph Neural Networks

• Marc Vincent
• Amal El Fallah Seghrouchni
• Vincent Corruble
• Narayan Bernardin
• Rami Kassab
• Frédéric Barbaresco

Many potential applications of reinforcement learning involve complex, structured environments. Some of these problems can be analyzed as factored MDPs, where the dynamics are decomposed into locally independent state transitions and the reward is rewritten as the sum of local rewards. However, in some scenarios, these rewards may represent conflicting objectives, so that the problem is better interpreted as a multi-objective one, with a weight associated to each reward. To deal with such multi-objective factored MDPs, we propose a method which combines the use of graph neural networks, to process structured representations, and vector-valued Q-learning. We show that our approach empirically outperforms methods that directly learn from the scalarized reward and demonstrate its ability to generalize to different weights and number of entities.

ECAI Conference 2014 Conference Paper

ADS2: Anytime Distributed Supervision of Distributed Systems that Face Unreliable or Costly Communication

• Cédric Herpson
• Amal El Fallah Seghrouchni
• Vincent Corruble

Nowadays industrial process are mainly distributed, and their supervision systems are still centralized. Consequently, when communications are disrupted, it slows down or stops the supervision process. To allow the anytime supervision of such systems, we propose a distributed approch based on a multi-agent system where each supervision agent autonomously handles both diagnosis and repair on a given location. We demonstrate the advantage of our proposal and evaluates ADS2 using an industrial case-study. Experiments demonstrate the relevance of our approach with an overall reduction of the supervised system down-time of 34%.

AAMAS Conference 2012 Conference Paper

The "Resource" Approach to Emotion

• Sabrina Campano
• Nicolas Sabouret
• Etienne de Sevin
• Vincent Corruble

In this paper, we present a model for the simulation of affective behaviour without emotion categories, centered around the theory of conservation of resources [3]. Each agent can acquire or protect resources, and behaviour choice depends on resources state, as well as agent’s needs and preferences. We also present a first evaluation.

AAMAS Conference 2011 Conference Paper

Dynamic Level of Detail for Large Scale Agent-Based Urban Simulations

• Laurent Navarro
• Fabien Flacher
• Vincent Corruble

Large scale agent-based simulations typically face a trade-off between the level of detail in the representation of each agent and the scalability seen as the number of agents that can be simulated with the computing resources available. In this paper, we aim at bypassing this trade-off by considering that the level of detail is itself a parameter that can be adapted automatically and dynamically during the simulation, taking into account elements such as user focus, or specific events. We introduce a framework for such a methodology, and detail its deployment within an existing simulator dedicated to the simulation of urban infrastructures. We evaluate the approach experimentally along two criteria: (1) the impact of our methodology on the resources (CPU use), and (2) an estimate of the dissimilarity between the two modes of simulation, i. e. with and without applying our methodology. Initial experiments show that a major gain in CPU time can be obtained for a very limited loss of consistency.

AAMAS Conference 2004 Conference Paper

Multi-Agent Patrolling with Reinforcement Learning

• Hugo Santana
• Geber Ramalho
• Vincent Corruble
• Bohdana Ratitch

AIJ Journal 1997 Journal Article

Induction and the discovery of the causes of scurvy: a computational reconstruction

• Vincent Corruble
• Jean-Gabriel Ganascia

AAAI Conference 1996 Conference Paper

The Discovery of the Causes of Leprosy: A Computational Analysis

• Vincent Corruble

The role played by the inductive inference has been studied extensively in the field of Scientific Discovery. The work presented here tackles the problem of induction in medical research. The discovery of the causes of leprosy is analyzed and simulated using computational means. An inductive algorithm is proposed, which is successful in simulating some essential steps in the progress of the understanding of the disease. It also allows us to simulate the false reasoning of previous centuries through the introduction of some medical a priori inherited form archaic medicine. Corroborating previous research, this problem illustrates the importance of the social and cultural environment on the way the inductive inference is performed in medicine.