Riccardo De Santi

I am a PhD student in Machine Learning at the ETH AI Center. I am lucky to be advised by Andreas Krause (Learning and Adaptive Systems group), Niao He (Optimization and Decision Intelligence group), and Kjell Jorner (Digital Chemistry Laboratory). I am also part of the Institute of Machine Learning at ETH. During my Bachelor I have started my research journey in Reinforcement Learning with prof. Marcello Restelli at Politecnico di Milano. Afterwards, during a MS in Machine Learning and Theoretical CS at ETH, I have done visitings at the University of Oxford and Imperial College London, both times under the supervision of profs. Michael Bronstein and Marcello Restelli. My research has been recently awarded with an Outstanding Paper Award at ICML 2022.

research interests

I am broadly interested in the foundations of algorithmic decision-making and its applications in automatic scientific discovery. This spans a wide spectrum of areas including:

Decision Making Under Uncertainty (Reinforcement/Active Learning, Bayesian Optimization, Bandits)
Optimal Experimental Design
Submodular and Non-Convex Optimization
Causality and Geometric Machine Learning

I strive to design reliable algorithms with guarantees leading to theoretical understanding of the underlying problems as well as relevant for real world applications mostly related with digital chemistry, including molecular design, drug discovery, and experimental design in chemical spaces.

If you are a MS student wishing to work with me, feel free to contact me here.

Contacts: Google Scholar | Twitter | LinkedIn | Github | rdesanti [at] ethz [dot] ch

news

Nov 23, 2023	My TEDx talk Beyond the Limits of the Mind: Scientific Discovery Reimagined is now available online!
Nov 22, 2023	On December 1st I will ufficially start my PhD at the ETH AI Center advised by Andreas Krause, Niao He, and Kjell Jorner.
Oct 27, 2023	Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning accepted at the Causal Representation Learning Workshop at NeurIPS 2023!

selected publications

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning

Mirco Mutti, Riccardo De Santi, Marcello Restelli, and 2 more authors

2023

Causal Representation Learning Workshop at NeurIPS 2023

Bibtex PDF

@article{mutti2023exploiting,
  title = {Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning},
  author = {Mutti, Mirco and De Santi, Riccardo and Restelli, Marcello and Marx, Alexander and Ramponi, Giorgia},
  workshop = {Causal Representation Learning Workshop at NeurIPS 2023},
  year = {2023},
}

JMLR

Convex Reinforcement Learning in Finite Trials

Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, and 1 more author

Journal of Machine Learning Research (JMLR), 2023

Bibtex PDF

@article{mutti2023convex,
  title = {Convex Reinforcement Learning in Finite Trials},
  author = {Mutti, Mirco and De Santi, Riccardo and De Bartolomeis, Piersilvio and Restelli, Marcello},
  journal = {Journal of Machine Learning Research (JMLR)},
  year = {2023},
}

AAAI

Provably efficient causal model-based reinforcement learning for systematic generalization

Mirco Mutti*, Riccardo De Santi*, Emanuele Rossi, and 3 more authors

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023

Workshop on Spurious Correlations, Invariance, and Stability at ICML 2022 and A Causal View on Dynamical Systems Workshop at NeurIPS 2022

Bibtex PDF

@inproceedings{mutti2023provably,
  title = {Provably efficient causal model-based reinforcement learning for systematic generalization},
  author = {Mutti*, Mirco and De Santi*, Riccardo and Rossi, Emanuele and Calderon, Juan Felipe and Bronstein, Michael and Restelli, Marcello},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  workshop = {Workshop on Spurious Correlations, Invariance, and Stability at ICML 2022 and A Causal View on Dynamical Systems Workshop at NeurIPS 2022},
}

Non-Markovian Policies for Unsupervised Reinforcement Learning in Multiple Environments

Pietro Maldini*, Mirco Mutti*, Riccardo De Santi, and 1 more author

2022

Decision Awareness in Reinforcement Learning Workshop and First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022

Bibtex PDF

@inproceedings{maldini2022non,
  title = {Non-Markovian Policies for Unsupervised Reinforcement Learning in Multiple Environments},
  author = {Maldini*, Pietro and Mutti*, Mirco and De Santi, Riccardo and Restelli, Marcello},
  workshop = {Decision Awareness in Reinforcement Learning Workshop and First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022},
  year = {2022},
}

NeurIPS

Challenging common assumptions in convex reinforcement learning

Mirco Mutti*, Riccardo De Santi*, Piersilvio De Bartolomeis, and 1 more author

Advances in Neural Information Processing Systems (NeurIPS), 2022

Complex Feedback in Online Learning (CFOL) Workshop at ICML 2022

Bibtex PDF

@article{mutti2022challenging,
  title = {Challenging common assumptions in convex reinforcement learning},
  author = {Mutti*, Mirco and De Santi*, Riccardo and De Bartolomeis, Piersilvio and Restelli, Marcello},
  journal = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  workshop = {Complex Feedback in Online Learning (CFOL) Workshop at ICML 2022},
}

ICML

The importance of non-markovianity in maximum state entropy exploration

Mirco Mutti*, Riccardo De Santi*, and Marcello Restelli

International Conference on Machine Learning (ICML), 2022

Outstanding Paper Award at ICML 2022

ICML Workshop on Reinforcement Learning Theory, 2021

Bibtex Talk PDF

@inproceedings{mutti2022importance,
  title = {The importance of non-markovianity in maximum state entropy exploration},
  author = {Mutti*, Mirco and De Santi*, Riccardo and Restelli, Marcello},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  award = {Outstanding Paper Award at ICML 2022},
  workshop = {ICML Workshop on Reinforcement Learning Theory, 2021},
  talk = {https://icml.cc/virtual/2022/oral/16290},
}