Giorgia Ramponi

Giorgia Ramponi

PhD candidate

Politecnico di Milano

Biography

Hi! I am a PhD candidate in Computer Science at Politecnico di Milano, advised by Marcello Restelli. In 2017, I obtained a Master of Science in Computer Science with the Honours Programme (110/110 cum laude) from la Sapienza advised by Flavio Chierichetti. My research interests lie in machine learning and mathematical modelling, with a focus on reinforcement learning and multiagent learning.

In my previous life I worked on Social Network Analysis with Marco Brambilla and Stefano Ceri, and on Networking with Gaia Maselli.

Interests

  • Machine Learning
  • Reinforcement Learning
  • Mathematical Modeling

Education

  • PhD in Computer Science, 2017 - on going

    Politecnico di Milano

  • Visiting PhD, 2018

    Harvard University

  • MSc in Computer Science (110/110 cum laude), 2015 - 2017

    La Sapienza University of Rome

  • BSc in Computer Science (110/110 cum laude), 2012 - 2015

    La Sapienza University of Rome

News

ONE PAPER ACCEPTED AT AAAI2021 workshop

Our paper ‘‘Online Learning in Non-Cooperative Configurable Markov Decision Process’’ has been accepted at RLG 2021 workshop at AAAI

ONE PAPER ACCEPTED AT AAAI2021

Our paper ‘‘Newton Optimization on Helmholtz Decomposition for Continuous Games’’ has been accepted at AAAI2021

TWO PAPERS ACCEPTED AT NeurIPS workshops

Our paper ‘‘Handling Non-Stationary Experts in Inverse Reinforcement Learning: A Water System Control Case Study’’ has been accepted at Challenges of Real World Reinforcement Learning Workshop, and ‘‘Newton-based Policy Optimization for Games’’ has been accepted at CooperativeAI workshop.

ONE PAPER ACCEPTED AT INLG 2020

Our paper ‘‘Controlled Text Generation with Adversarial Learning’’ has been accepted at INLG 2020

ONE PAPER ACCEPTED AT NeurIPS 2020

Our paper Inverse Reinforcement Learning from a Gradient-based Learner has been accepted at NeurIPS 2020

Publications

(2021). Newton Optimization on Helmholtz Decomposition for Continuous Games. to appear at AAAI.

PDF

(2020). Inverse Reinforcement Learning from a Gradient-based Learner. Advances in Neural Information Processing Systems.

PDF

(2020). Content-based characterization of online social communities. Information Processing & Management Journal.

PDF

(2020). Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions. International Conference on Artificial Intelligence and Statistics.

PDF

(2019). Assigning users to domains of interest based on content and network similarity with champion instances. Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.

PDF