Luca Viano

Research Interests:

  • Reinforcement Learning
  • Imitation Learning
  • Optimization

 

Biography

Since September 2021, I am an ELLIS PhD Fellow supervised by Volkan Cevher and co-supervised by Gergely Neu. My first PhD year was kindly supported by the EDIC Excellence Fellowship.

Before that, I worked as Data Scientist at Datapred, I obtained a MSc in Computational Science and Engineering from EPFL and a Bachelor in Engineering Physics from Politecnico di Torino, Italy. Cycling is my main hobby.

Publications with LIONS

 

Imitation Learning in Discounted Linear MDPs without exploration assumptions

L. Viano; E. P. Skoulakis; V. Cevher 

2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.

Detailed record

Full text

Alternation makes the adversary weaker in two-player games

V. Cevher; A. Cutkosky; A. Kavis; G. Piliouras; E. P. Skoulakis et al. 

2023.  37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orlean, USA, December 10-16. 2023.

Detailed record

Full text

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

I. Panageas; E. P. Skoulakis; L. Viano; X. Wang; V. Cevher 

2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.

Detailed record

Full text

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

F. Liu; L. Viano; V. Cevher 

2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.

Detailed record

Full text

A Natural Actor-Critic Framework for Zero-Sum Markov Games

A. Alacaoglu; L. Viano; N. He; V. Cevher 

2022. 39th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.

Detailed record

Full text

Contact

e-mail address: [email protected]

EPFL people page

Access map