6 citations · 27 across the 29 of their papers we have counts for
30 papers
The Dynamics of Quasiregular Neural Learning
Matthia Sabatelli
Many learning problems combine a dominant regularity with systematic exceptions. Motivated by U-shaped learning in language acquisition, we study this interaction in controlled qua…
Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning
Viktor Veselý, Aleksandar Todorov, Erwan Escudie +1
Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood. We identify a…
Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning
Aleksandar Todorov, Matthia Sabatelli
Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intr…
An -Optimal Sequential Approach for Solving zs-POSGs
Erwan C. Escudie, Matthia Sabatelli, Jilles S. Dibangoye
While recent reductions of zero-sum partially observable stochastic games (zs-POSGs) to transition-independent stochastic games (TI-SGs) theoretically admit dynamic programming, pr…
ε-Optimally Solving Two-Player Zero-Sum POSGs
Erwan Christian Escudie, Matthia Sabatelli, Olivier Buffet +1
We present a novel framework for ε-optimally solving two-player zero-sum partially observable stochastic games (zs-POSGs). These games pose a major challenge due to the absence of…
On The Presence of Double-Descent in Deep Reinforcement Learning
Viktor Veselý, Aleksandar Todorov, Matthia Sabatelli
The double descent (DD) paradox, where over-parameterized models see generalization improve past the interpolation point, remains largely unexplored in the non-stationary domain of…
On the Generalisation of Koopman Representations for Chaotic System Control
Kyriakos Hjikakou, Juan Diego Cardenas Cartagena, Matthia Sabatelli
This paper investigates the generalisability of Koopman-based representations for chaotic dynamical systems, focusing on their transferability across prediction and control tasks.…
Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
Aleksandar Todorov, Juan Cardenas-Cartagena, Rafael F. Cunha +2
Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement l…
Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning
Massimiliano Falzari, Matthia Sabatelli
Deep Reinforcement Learning (DRL) systems often tend to overfit to early experiences, a phenomenon known as the primacy bias (PB). This bias can severely hinder learning efficiency…
Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting
Josh Bruegger, Diana Ioana Catana, Vanja Macovaz +3
The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situatio…
Upside-Down Reinforcement Learning for More Interpretable Optimal Control
Juan Cardenas-Cartagena, Massimiliano Falzari, Marco Zullich +1
Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-…
Video-Driven Graph Network-Based Simulators
Franciszek Szewczyk, Gilles Louppe, Matthia Sabatelli
Lifelike visualizations in design, cinematography, and gaming rely on precise physics simulations, typically requiring extensive computational resources and detailed physical input…
Measuring Orthogonality as the Blind-Spot of Uncertainty Disentanglement
Ivo Pascal de Jong, Andreea Ioana Sburlea, Matthia Sabatelli +1
Aleatoric (data) and epistemic (knowledge) uncertainty are textbook components of Uncertainty Quantification. Jointly estimating these components has been shown to be problematic a…
Smaller Batches, Bigger Gains? Investigating the Impact of Batch Sizes on Reinforcement Learning Based Real-World Production Scheduling
Arthur Müller, Felix Grumbach, Matthia Sabatelli
Production scheduling is an essential task in manufacturing, with Reinforcement Learning (RL) emerging as a key solution. In a previous work, RL was utilized to solve an extended p…
-Optimally Solving Zero-Sum POSGs
Erwan Escudie, Matthia Sabatelli, Jilles Dibangoye
A recent method for solving zero-sum partially observable stochastic games (zs-POSGs) embeds the original game into a new one called the occupancy Markov game. This reformulation a…
VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts
Marius Captari, Remo Sasso, Matthia Sabatelli
Despite the considerable attention given to the questions of \textit{how much} and \textit{how to} explore in deep reinforcement learning, the investigation into \textit{when} to e…
Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation
Tsegaye Misikir Tashu, Eduard-Raul Kontos, Matthia Sabatelli +1
Recommendation systems, for documents, have become tools to find relevant content on the Web. However, these systems have limitations when it comes to recommending documents in lan…
Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning
Arthur Müller, Matthia Sabatelli
Reinforcement Learning (RL) has been widely explored in Traffic Signal Control (TSC) applications, however, still no such system has been deployed in practice. A key barrier to pro…
Learning Perceptive Bipedal Locomotion over Irregular Terrain
Bart van Marum, Matthia Sabatelli, Hamidreza Kasaei
In this paper we propose a novel bipedal locomotion controller that uses noisy exteroception to traverse a wide variety of terrains. Building on the cutting-edge advancements in at…
Factors of Influence of the Overestimation Bias of Q-Learning
Julius Wagenbach, Matthia Sabatelli
We study whether the learning rate , the discount factor and the reward signal have an influence on the overestimation bias of the Q-Learning algorithm. Our preliminary…
Machine Learning Students Overfit to Overfitting
Matias Valdenegro-Toro, Matthia Sabatelli
Overfitting and generalization is an important concept in Machine Learning as only models that generalize are interesting for general applications. Yet some students have trouble l…
How Well Do Vision Transformers (VTs) Transfer To The Non-Natural Image Domain? An Empirical Study Involving Art Classification
Vincent Tonkes, Matthia Sabatelli
Vision Transformers (VTs) are becoming a valuable alternative to Convolutional Neural Networks (CNNs) when it comes to problems involving high-dimensional and spatially organized i…
Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking
Arthur Müller, Matthia Sabatelli
Reinforcement learning (RL) for traffic signal control (TSC) has shown better performance in simulation for controlling the traffic flow of intersections than conventional approach…
Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning
Remo Sasso, Matthia Sabatelli, Marco A. Wiering
A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes…