Current PhD Students

  • Tao Zhang
  • Samin Nili-Ahmadabadi
  • Amit Sinha
  • Borna Sayedana (co-supervised with Prof. Peter Caines)
  • Raihan Seraj (co-supervised with Prof. Jerome Le Ny)

Current Master's Students

  • Edwin Meriaux
  • Reihaneh Ghoroghchian
group photo 2017

Group photo (2021). Top Row (L to R): Aditya, Chenyu, Mohammad, Berk. Middle Row: Jayakumar, Cheng, Borna, Fatih. Bottom Row: Nima, Amit, Raihan.

group photo 2017

Group photo (2017). From L to R: Borna, Nima, Jhelum, Raihan, Aditya, Jayakumar, Mohammad.

Graduated PhD Students

Graduated Master's Students

  • Annavaleria Ardito, March 2024. Study and implementation of multiple mobile robots control.
  • Berk Bozkurt, Apr 2024. Weighted-norm bounds on model approximation in MDPs with unbounded per-step cost.
  • Erfan SeyedSalehi, Apr 2023. Approximate information state for model based recurrent Q-learning.
  • Sharareh Younesian (co-supervised with Prof. Peter Caines), Dec 2022. Structure-aware reinforcement learning for searching optimal monotone policies.
  • Chenyu Liu, June 2022. Optimism in $Q$-learning: Unified overview and comparison.
  • Alper ├ľker (co-supervised with Prof. Peter Caines), April 2021. Distributed Kalman Filtering and Estimation.
  • Anirudha Jitani (co-supervised with Prof. Doina Precup), April 2021. Intelligent node-overload protection in mobile edge computing using reinforcement learning.
  • Amit Sinha, Dec 2020. Reinforcement learning in POMDPs.
  • Samin Yeasar Arnob, May 2020. Improving Robustness in Inverse Reinforcement Learning.
  • Borna Sayedana, Aug 2019. Monotonicity of value function and optimal policy in cross-layer design of communication systems.
  • Raihan Seraj, April 2019. Learning in the presence of partial observability and concept drifts.
  • Romina Hassani, Dec 2018. Social learning and distributed hypothesis testing.
  • Sebin Mathew, Aug 2018. Dual decomposition algorithms for sensor scheduling.
  • Ming Lei, Aug 2017. Optimal policies for energy storage in microgrids.
  • Aide Zhou, Apr 2017. Monte Carlo simulations for remote state estimation.
  • Calvin Ma, Aug 2016. Multi-armed bandits for MPSoC design space exploration.
  • Can Cui, Aug 2015. On computing optimal thresholds for sequential hypothesis testing.
  • Mehnaz Mannan, Apr 2015. Finite-state approximation for a class of POMDPs and comparison of reinforcement learning algorithms for managing energy storage in renewable generation.
  • Prokopis Prokopiou, Aug 2014. An estimation based allocation rule with super-linear regret and finite lock-on time for dependent multi-armed bandits.