Back
  1. Home
  2. Profile of Matthia Sabatelli (ULiège)
Profil

Sabatelli Matthia

See author's contact details
Main Referenced Co-authors
Geurts, Pierre  (9)
Kestemont, Mike (4)
Louppe, Gilles  (4)
Wiering, Marco (4)
Daelemans, Walter (2)
Main Referenced Keywords
Transfer Learning (4); Deep Reinforcement Learning (3); Deep Convolutional Neural Networks (2); Model-free Deep Reinforcement Learning (2); Art Classification (1);
Main Referenced Disciplines
Computer science (11)

Publications (total 11)

The most downloaded
419 downloads
Sabatelli, M., Louppe, G., Geurts, P., & Wiering, M. (2020). The Deep Quality-Value Family of Deep Reinforcement Learning Algorithms. International Joint Conference on Neural Networks (IJCNN 2020). https://hdl.handle.net/2268/249809

The most cited

3 citations (Scopus®)

Sabatelli, M., Kestemont, M., & Geurts, P. (2021). On the Transferability of Winning Tickets in Non-Natural Image Datasets. 16th International Conference on Computer Vision Theory and Applications - VISAPP 2021. https://hdl.handle.net/2268/255720

Sabatelli, M. (2022). Contributions to Deep Transfer Learning: from Supervised to Reinforcement Learning [Doctoral thesis, ULiège - Université de Liège]. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/267842

Sabatelli, M., & Geurts, P. (2021). On The Transferability of Deep-Q Networks. Deep Reinforcement Learning Workshop of the 35th Conference on Neural Information Processing Systems.
Peer reviewed

Sabatelli, M., Kestemont, M., & Geurts, P. (2021). On the Transferability of Winning Tickets in Non-Natural Image Datasets. 16th International Conference on Computer Vision Theory and Applications - VISAPP 2021.
Peer reviewed

Leroy, P., Ernst, D., Geurts, P., Louppe, G., Pisane, J., & Sabatelli, M. (2021). QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning. In Proceedings of the AAAI-21 Workshop on Reinforcement Learning in Games (pp. 8).
Peer reviewed

Sabatelli, M., Banar, N., Cocriamont, M., Coudyzer, E., Lasaracina, K., Daelemans, W., Geurts, P., & Kestemont, M. (February 2021). Advances in Digital Music Iconography: Benchmarking the detection of musical instruments in unrestricted, non-photorealistic images from the artistic domain. Digital Humanities Quarterly, 15 (1).
Peer Reviewed verified by ORBi

Sabatelli, M., Louppe, G., Geurts, P., & Wiering, M. (2020). The Deep Quality-Value Family of Deep Reinforcement Learning Algorithms. International Joint Conference on Neural Networks (IJCNN 2020).
Peer reviewed

Hammond, T., Schaap, D. J., Sabatelli, M., & Wiering, M. (2020). Forest Fire Control with Learning from Demonstration and Reinforcement Learning. International Joint Conference on Neural Networks (IJCNN 2020).
Peer reviewed

Sabatelli, M., Louppe, G., Geurts, P., & Wiering, M. (2019). Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms. Advances in Neural Information Processing Systems.
Peer Reviewed verified by ORBi

Sabatelli, M., Kestemont, M., & Geurts, P. (October 2019). Improving the Training of Deep Convolutional Neural Networks for Art Classification: from Transfer Learning to Multi-Task Learning [Paper presentation]. The 6th Digital Humanities (DH) Benelux Conference.

Sabatelli, M., Louppe, G., Geurts, P., & Wiering, M. (2018). Deep Quality Value (DQV) Learning. Advances in Neural Information Processing Systems.
Peer Reviewed verified by ORBi

Sabatelli, M., Kestemont, M., Daelemans, W., & Geurts, P. (2018). Deep Transfer Learning for Art Classification Problems. European Conference on Computer Vision (ECCV), 4th Workshop on Computer VISion for ART Analysis (VISART IV).
Peer reviewed

Contact ORBi