Matthia Sabatelli

52 papers B 2C 5Journal 29Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	An ε-Optimal Sequential Approach for Solving zs-POSGs. CoRR Jilles Steeve Dibangoye, Matthia Sabatelli, Erwan Escudie
2025	—	`conf`	A Study on the Faithfulness of Feature Attribution Explanations in Pruned Vision-Based Multi-Task Learning. xAI (Late-breaking Work, Demos, Doctoral Consortium) Xenia Demetriou, Sophie Sananikone, Vojislav Tobias Westmoreland, Matthia Sabatelli, Marco Zullich
2025	—	`conf`	Cross-Lingual Document Recommendations with Transformer-Based Representations: Evaluating Multilingual Models and Mapping Techniques. COLING Workshops Tsegaye Misikir Tashu, Eduard-Raul Kontos, Matthia Sabatelli, Matias Valdenegro-Toro
2025	J	`jnl`	Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning. CoRR Massimiliano Falzari, Matthia Sabatelli
2025	—	`conf`	Interpretable Function Approximation with Gaussian Processes in Value-Based Model-Free Reinforcement Learning. NLDL Matthijs van der Lende, Matthia Sabatelli, Juan Cardenas-Cartagena
2025	C	`conf`	Large-Image Object Detection for Fine-Grained Recognition of Punches Patterns in Medieval Panel Painting. EvoMUSART Josh Bruegger, Diana Ioana Catana, Vanja Macovaz, Matias Valdenegro-Toro, Matthia Sabatelli, Marco Zullich
2025	J	`jnl`	Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting. CoRR Josh Bruegger, Diana Ioana Catana, Vanja Macovaz, Matias Valdenegro-Toro, Matthia Sabatelli, Marco Zullich
2025	J	`jnl`	On The Presence of Double-Descent in Deep Reinforcement Learning. CoRR Viktor Veselý, Aleksandar Todorov, Matthia Sabatelli
2025	J	`jnl`	On the Generalisation of Koopman Representations for Chaotic System Control. CoRR Kyriakos Hjikakou, Juan Diego Cardenas Cartagena, Matthia Sabatelli
2025	C	`conf`	Optimizing Initial Qubit Mappings Under Fixed Gate Error Rates Using Deep Reinforcement Learning. I4CS Rares Adrian Oancea, Stan van der Linde, Willem de Kok, Matthia Sabatelli, Sebastian Feld
2025	—	`conf`	Physics-Informed Graph Neural Networks for Air Pollution Forecasting in the Netherlands. ML-DE Nikolas Assiotis, Rachel Hau, Valentijn Oldenburg, Rik Verbiest, Julian Koellermeier, Matthia Sabatelli, Juan Cardenas-Cartagena
2025	J	`jnl`	Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning. CoRR Aleksandar Todorov, Juan Cardenas-Cartagena, Rafael Fernandes Cunha, Marco Zullich, Matthia Sabatelli
2025	J	`jnl`	Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning. Trans. Mach. Learn. Res. Aleksandar Todorov, Juan Cardenas-Cartagena, Rafael Fernandes Cunha, Marco Zullich, Matthia Sabatelli
2025	—	`conf`	Upside-Down Reinforcement Learning for More Interpretable Optimal Control. ICAART (1) Juan Cardenas-Cartagena, Massimiliano Falzari, Marco Zullich, Matthia Sabatelli
2025	J	`jnl`	ε-Optimally Solving Two-Player Zero-Sum POSGs. CoRR Erwan Escudie, Matthia Sabatelli, Olivier Buffet, Jilles Steeve Dibangoye
2024	—	`conf`	Contextual Online Imitation Learning (COIL): Using Guide Policies in Reinforcement Learning. ICAART (3) Alexander Hill, Marc Groefsema, Matthia Sabatelli, Raffaella Carloni, Marco Grzegorczyk
2024	J	`jnl`	Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation. CoRR Tsegaye Misikir Tashu, Eduard-Raul Kontos, Matthia Sabatelli, Matias Valdenegro-Toro
2024	C	`conf`	Smaller Batches, Bigger Gains? Investigating the Impact of Batch Sizes on Reinforcement Learning Based Real-World Production Scheduling. ETFA Arthur Müller, Felix Grumbach, Matthia Sabatelli
2024	J	`jnl`	Smaller Batches, Bigger Gains? Investigating the Impact of Batch Sizes on Reinforcement Learning Based Real-World Production Scheduling. CoRR Arthur Müller, Felix Grumbach, Matthia Sabatelli
2024	J	`jnl`	Upside-Down Reinforcement Learning for More Interpretable Optimal Control. CoRR Juan Cardenas-Cartagena, Massimiliano Falzari, Marco Zullich, Matthia Sabatelli
2024	J	`jnl`	VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts. CoRR Marius Captari, Remo Sasso, Matthia Sabatelli
2024	J	`jnl`	Video-Driven Graph Network-Based Simulators. CoRR Franciszek Szewczyk, Gilles Louppe, Matthia Sabatelli
2024	J	`jnl`	ε-Optimally Solving Zero-Sum POSGs. CoRR Erwan Escudie, Matthia Sabatelli, Jilles Dibangoye
2023	—	`conf`	Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning. ITSC Arthur Müller, Matthia Sabatelli
2023	J	`jnl`	Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning. CoRR Arthur Müller, Matthia Sabatelli
2023	J	`jnl`	Learning Perceptive Bipedal Locomotion over Irregular Terrain. CoRR Bart van Marum, Matthia Sabatelli, Hamidreza Kasaei
2023	J	`jnl`	Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning. Trans. Mach. Learn. Res. Remo Sasso, Matthia Sabatelli, Marco A. Wiering
2022	—	`—`	Contributions to Deep Transfer Learning: from Supervised to Reinforcement Learning. Matthia Sabatelli
2022	J	`jnl`	Factors of Influence of the Overestimation Bias of Q-Learning. CoRR Julius Wagenbach, Matthia Sabatelli
2022	J	`jnl`	How Well Do Vision Transformers (VTs) Transfer To The Non-Natural Image Domain? An Empirical Study Involving Art Classification. CoRR Vincent Tonkes, Matthia Sabatelli
2022	—	`conf`	How Well Do Vision Transformers (VTs) Transfer to the Non-natural Image Domain? An Empirical Study Involving Art Classification. ECCV Workshops (1) Vincent Tonkes, Matthia Sabatelli
2022	—	`conf`	Machine Learning Students Overfit to Overfitting. Teaching ML Matias Valdenegro-Toro, Matthia Sabatelli
2022	J	`jnl`	Machine Learning Students Overfit to Overfitting. CoRR Matias Valdenegro-Toro, Matthia Sabatelli
2022	J	`jnl`	Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning. CoRR Remo Sasso, Matthia Sabatelli, Marco A. Wiering
2022	—	`conf`	Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking. ITSC Arthur Müller, Matthia Sabatelli
2022	J	`jnl`	Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking. CoRR Arthur Müller, Matthia Sabatelli
2021	J	`jnl`	Advances in Digital Music Iconography: Benchmarking the detection of musical instruments in unrestricted, non-photorealistic images from the artistic domain. Digit. Humanit. Q. Matthia Sabatelli, Nikolay Banar, Marie Cocriamont, Eva Coudyzer, Karine Lasaracina, Walter Daelemans, Pierre Geurts, Mike Kestemont
2021	J	`jnl`	Fractional Transfer Learning for Deep Model-Based Reinforcement Learning. CoRR Remo Sasso, Matthia Sabatelli, Marco A. Wiering
2021	J	`jnl`	On The Transferability of Deep-Q Networks. CoRR Matthia Sabatelli, Pierre Geurts
2021	—	`conf`	On the Transferability of Winning Tickets in Non-natural Image Datasets. VISIGRAPP (5: VISAPP) Matthia Sabatelli, Mike Kestemont, Pierre Geurts
2021	—	`conf`	Transfer Learning with Style Transfer between the Photorealistic and Artistic Domain. Computer Vision and Image Analysis of Art Nikolay Banar, Matthia Sabatelli, Pierre Geurts, Walter Daelemans, Mike Kestemont
2020	B	`conf`	Forest Fire Control with Learning from Demonstration and Reinforcement Learning. IJCNN Travis Hammond, Dirk Jelle Schaap, Matthia Sabatelli, Marco A. Wiering
2020	J	`jnl`	On the Transferability of Winning Tickets in Non-Natural Image Datasets. CoRR Matthia Sabatelli, Mike Kestemont, Pierre Geurts
2020	J	`jnl`	QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning. CoRR Pascal Leroy, Damien Ernst, Pierre Geurts, Gilles Louppe, Jonathan Pisane, Matthia Sabatelli
2020	B	`conf`	The Deep Quality-Value Family of Deep Reinforcement Learning Algorithms. IJCNN Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
2019	J	`jnl`	Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms. CoRR Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
2019	—	`conf`	Deep Quality-Value (DQV) Learning. BNAIC/BENELEARN Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
2018	C	`conf`	A Deep Convolutional Neural Network for Location Recognition and Geometry based Information. ICPRAM Francesco Bidoia, Matthia Sabatelli, Amirhossein Shantia, Marco A. Wiering, Lambert Schomaker
2018	J	`jnl`	Deep Quality-Value (DQV) Learning. CoRR Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
2018	—	`conf`	Deep Transfer Learning for Art Classification Problems. ECCV Workshops (2) Matthia Sabatelli, Mike Kestemont, Walter Daelemans, Pierre Geurts
2018	C	`conf`	Learning to Evaluate Chess Positions with Deep Neural Networks and Limited Lookahead. ICPRAM Matthia Sabatelli, Francesco Bidoia, Valeriu Codreanu, Marco A. Wiering
2014	—	`conf`	Correlation of significant places with self-reported state of bipolar disorder patients. MobiHealth Matthia Sabatelli, Venet Osmani, Oscar Mayora, Agnes Grünerbl, Paul Lukowicz