106 citations · 297 across the 23 of their papers we have counts for
11 papers · 1 filter
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
Marco Pratticò, Pietro Novelli, Massimiliano Pontil +1
Sparse rewards pose a central challenge in reinforcement learning, since agents receive no informative signal until they reach their goal. Intrinsic-reward methods address this iss…
kooplearn: A Scikit-Learn Compatible Library of Algorithms for Evolution Operator Learning
Giacomo Turri, Grégoire Pacreau, Giacomo Meanti +8
kooplearn is a machine-learning library that implements linear, kernel, and deep-learning estimators of dynamical operators and their spectral decompositions. kooplearn can model b…
Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
Giacomo Turri, Luigi Bonati, Kai Zhu +2
We introduce an encoder-only approach to learn the evolution operators of large-scale non-linear dynamical systems, such as those describing complex natural phenomena. Evolution op…
Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
Vladimir R. Kostic, Karim Lounici, Hélène Halconruy +3
Markov processes serve as a universal model for many real-world random processes. This paper presents a data-driven approach for learning these models through the spectral decompos…
Neural Conditional Probability for Uncertainty Quantification
Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau +3
We introduce Neural Conditional Probability (NCP), an operator-theoretic approach to learning conditional distributions with a focus on statistical inference tasks. NCP can be used…
Operator World Models for Reinforcement Learning
Pietro Novelli, Marco Pratticò, Massimiliano Pontil +1
Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL)…
A randomized algorithm to solve reduced rank operator regression
Giacomo Turri, Vladimir Kostic, Pietro Novelli +1
We present and analyze an algorithm designed for addressing vector-valued regression problems involving possibly infinite-dimensional input and output spaces. The algorithm is a ra…
Learning invariant representations of time-homogeneous stochastic dynamical systems
Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi +2
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that f…
Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
John Falk, Luigi Bonati, Pietro Novelli +2
Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, whi…
Sharp Spectral Rates for Koopman Operator Learning
Vladimir Kostic, Karim Lounici, Pietro Novelli +1
Nonlinear dynamical systems can be handily described by the associated Koopman operator, whose action evolves every observable of the system forward in time. Learning the Koopman o…
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
Vladimir Kostic, Pietro Novelli, Andreas Maurer +3
We study a class of dynamical systems modelled as Markov chains that admit an invariant distribution via the corresponding transfer, or Koopman, operator. While data-driven algorit…