Enrico Marchesini

5 papers · 2021–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

AAAI (2) ICLR (2) UAI (1)

Top co-authors

Davide Corsi (4) Alessandro Farinelli (4) Christopher Amato (1) Luca Marzari (1) Ferdinando Cicalese (1)

Research topics

Reinforcement Learning (4) Methods (4) Artificial Intelligence (3) Core AI (3) Deep Learning (2) Machine Learning (2) Learning Types · Deep Learning (2) Applications (1) Learning Types · Machine Learning (1) Optimization & Theory (1)

Keywords

formal verification (3) deep reinforcement learning (3) neural network verification (2) continuous control (2) evolutionary algorithm (2) constrained optimization (1) adversarial robustness (1) safe region (1) value function approximation (1) variance reduction (1) policy improvement (1) safe reinforcement learning (1) cost function (1) sample efficiency (1) soft update (1) interval algebra (1) safety-critical system (1) probabilistic guarantee (1) reachable set (1) reachable set analysis (1)

Papers

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees AAAI 2024 Improving Deep Policy Gradients with Value Function Search ICLR 2023 Exploring Safer Behaviors for Deep Reinforcement Learning AAAI 2022 Formal verification of neural networks for safety-critical tasks in deep reinforcement learning UAI 2021 Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning ICLR 2021