References of "Wehenkel, Antoine"
     in
Bookmark and Share    
Full Text
See detailIntroducing neuromodulation in deep neural networks to learn adaptive behaviours
Vecoven, Nicolas ULiege; Ernst, Damien ULiege; Wehenkel, Antoine ULiege et al

E-print/Working paper (2019)

In this paper, we propose a new deep neural network architecture, called NMD net, that has been specifically designed to learn adaptive behaviours. This architecture exploits a biological mechanism called ... [more ▼]

In this paper, we propose a new deep neural network architecture, called NMD net, that has been specifically designed to learn adaptive behaviours. This architecture exploits a biological mechanism called neuromodulation that sustains adaptation in biological organisms. This architecture has been introduced in a deep-reinforcement learning architecture for interacting with Markov decision processes in a meta-reinforcement learning setting where the action space is continuous. The deep-reinforcement learning architecture is trained using an advantage actor-critic algorithm. Experiments are carried on several test problems. Results show that the neural network architecture with neuromodulation provides significantly better results than state-of-the-art recurrent neural networks which do not exploit this mechanism. [less ▲]

Detailed reference viewed: 75 (24 ULiège)
Full Text
Peer Reviewed
See detailRecurrent machines for likelihood-free inference
Pesah, Arthur; Wehenkel, Antoine ULiege; Louppe, Gilles ULiege

Conference (2018, December 08)

Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function ... [more ▼]

Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function, most of the existing inference methods optimize the simulator parameters through a handcrafted iterative procedure that tries to make the simulated data more similar to the observations. In this work, we explore whether meta-learning can be used in the likelihood-free context, for learning automatically from data an iterative optimization procedure that would solve likelihood-free inference problems. We design a recurrent inference machine that learns a sequence of parameter updates leading to good parameter estimates, without ever specifying some explicit notion of divergence between the simulated data and the real data distributions. We demonstrate our approach on toy simulators, showing promising results both in terms of performance and robustness. [less ▲]

Detailed reference viewed: 33 (7 ULiège)
Full Text
Peer Reviewed
See detailAn App-based Algorithmic Approach for Harvesting Local and Renewable Energy Using Electric Vehicles
Dubois, Antoine; Wehenkel, Antoine ULiege; Fonteneau, Raphaël ULiege et al

in Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017) (2017, February)

The emergence of electric vehicles (EVs), combined with the rise of renewable energy production capacities, will strongly impact the way electricity is produced, distributed and consumed in the very near ... [more ▼]

The emergence of electric vehicles (EVs), combined with the rise of renewable energy production capacities, will strongly impact the way electricity is produced, distributed and consumed in the very near future. This position paper focuses on the problem of optimizing charging strategies for a fleet of EVs in the context where a significant amount of electricity is generated by (distributed) renewable energy. It exposes how a mobile application may offer an efficient solution for addressing this problem. This app can play two main roles. Firstly, it would incite and help people to play a more active role in the energy sector by allowing photovoltaic (PV) panel owners to sell their electrical production directly to consumers, here the EVs’ agents. Secondly, it would help distribution system operators (DSOs) or transmission system operators (TSOs) to modulate more efficiently the load by allowing them to influence EV charging behaviour in real time. Finally, the present paper advocates for the introduction of a two-sided market-type model between EV drivers and electricity producers. [less ▲]

Detailed reference viewed: 1077 (142 ULiège)