Gian Antonio Susto — accepted AI-conference papers

2026

Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd “AI Olympics with RealAIGym” Competition

Felix Wiebe, Niccolò Turcato, Alberto Dalla Libera, Jean Seong Bjorn Choe, Bumkyu Choi, Tim Faust +15

ICRA 2026poster

In robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and …

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations

Davide Sartor, Alberto Sinigaglia, Gian Antonio Susto

ICML 2025poster

Imposing input-output constraints in multi-layer perceptrons (MLPs) plays a pivotal role in many real world applications. Monotonicity in particular is a common requirement in applications that need transparent and robust machine learning models. Conventional techniques for imposing monotonicity in…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Simple and Effective Specialized Representations for Fair Classifiers

Alberto Sinigaglia, Davide Sartor, Marina Ceccon, Gian Antonio Susto

NeurIPS 2025poster

Fair classification is a critical challenge that has gained increasing importance due to international regulations and its growing use in high-stakes decision-making settings. Existing methods often rely on adversarial learning or distribution matching across sensitive groups; however, adversarial l…

Cited by 0 Source ↗Scholar ↗

2021

Adversarial Training Reduces Information and Improves Transferability

Matteo Terzi, Alessandro Achille, Marco Maggipinto, Gian Antonio Susto

AAAI 2021technical

Recent results show that features of adversarially trained networks for classification, in addition to being robust, enable desirable properties such as invertibility. The latter property may seem counter-intuitive as it is widely accepted by the community that classification models should only cap…

Cited by 27 Source ↗PDF ↗Scholar ↗

2021

AutoSS: A Deep Learning-Based Soft Sensor for Handling Time-Series Input Data

Nicolò Bargellesi, Alessandro Beghi, Mirco Rampazzo, Gian Antonio Susto

RA-L 2021

Soft Sensors are data-driven technologies that allow to have estimations of quantities that are impossible or costly to be measured. Unfortunately, the design of effective soft sensors is heavily impacted by time-consuming feature engineering steps that may lead to sub-optimal information, especiall

Cited by 8 Source ↗Scholar ↗

2020

Proximal Deterministic Policy Gradient

Marco Maggipinto, Gian Antonio Susto, Pratik Chaudhari

IROS 2020poster

This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms. First, we formulate off-policy RL as a stochastic proximal point iteration. The target network plays the role of the variable of optimization and the value network computes the proximal operator…

Cited by 4 Source ↗Scholar ↗