d-corsi,Davide Corsi,dcorsi_,github

Hi there 👋

I am a Postdoctoral Researcher at University of California: Irvine, in the Intelligent Dynamics Lab under the supervision of Prof. Roy Fox. Previously, I worked as a visiting researcher under the supervision of Prof. Guy Katz at the Hebrew University of Jerusalem and I obtained my PhD at the University of Verona advised by Prof. Alessandro Farinelli.

Research Interests 🔭

My research interests focus on developing novel Deep Reinforcement Learning (DRL) methods applied to robotics, with a particular emphasis on the generation of reliable systems in safety-critical contexts. As an essential aspect of my work, I constantly try to merge theoretical research with practical application to real-world robotic problems.

📫 Contact 📫

Website: https://d-corsi.github.io/
Google Scholar: https://scholar.google.com/citations?user=chv2d8IAAAAJ&hl=en
Mail: [email protected]

Davide Corsi's Projects

ai-lab

Code for the AI lab course 2021/2022 - University of Verona

basicrl

A basic Tensorflow 2 implementation of the standard reinforcement learning algorithms, designed to solve gym-like environments.

eprove

This is the python implementation of ϵ-ProVe, a tool for the "AllDNN-Verification Problem" (i.e., the problem of computing the set of all the areas that do not result in a violation for a given DNN and a safety property). ϵ-ProVe is an approximation approach that provides provable (probabilistic) guarantees on the returned areas.

franka-ddqn

Neural network based controller for the redundant 7DOF robotic manipulator FRANKA

lambda-ppo

Implementation of the lambda-PPO algorithm, an improved version of the standard Lagrangian Proximal Policy Optimization.

networkverifier

A set of algorithms for the formal verification and analysis of Neural Networks, implemented in Python.

prove

A Python implementation of ProVe. ProVe is a formal verifier for safety property for Artificial Neural Networks, presented at the 37th conference on Uncertainty in Artificial Intelligence.