Aymeric CÔME

I am a PhD student in team Devine at Inria center at Rennes University , where I am working with Loïc HÉLOUËT and Éric FABRE on approximation schemes for the control of large Markov Decision Processes.

I did my master thesis in the DeLTA team of the University of Copenhagen where I was supervised by Mohammad Sadegh TALEBI , during which we looked for tight convergence bonds for Q-Learning in semi-Markov Decision Processes. I then graduated from the Master Data Science in Lille.

A Floyd Warshall Approach to Value Computation in Markov Decision Processes.
Côme A.*, Fabre É.*, Hélouët L.* (* = Equal Contribution)
QEST'24 | Quantitative Evaluation of SysTems
proceedings

Scaling Up Q-Learning via Exploiting State-Action Equivalence
Lyu Y., Côme A., Zhang Y., Talebi M.S.
Entropy 2023
pdf| proceedings| cite

Extracting Frequent (Closed) Seasonal Gradual Patterns using Closed Itemset Mining
Côme A., Lonlac J.
ICTAI'21 | 33rd International Conference on Tools with Artificial Intelligence
proceedings| cite

This website was made from the template provided by Sebastin SANTY.