Gersi Doko

Kingsbury N229

33 Academic Way

Durham, New Hampshire 03824

Hi! I’m Gersi Doko, research assistant and member of the RL^2 lab at the University of New Hampshire. I am a Ph.D. student in Computer Science. My research interests include reinforcement learning, Bayesian decision-making, and machine learning. I am currently working on developing algorithms for offline reinforcement learning.

news

Apr 23, 2026	Risk-Averse Total-Reward Reinforcement Learning accepted into NeurIPS!
Sep 01, 2025	Away on internship at Amazon NYC! Working on LLM inferenece optimization and scaling.
Oct 16, 2024	Interdisciplinary Deep RL Work submitted to the Resources, Conservation and Recycling Journal.
May 01, 2024	Paper accepted to the Reinforcement Learning Journal!
May 30, 2022	Began my PhD at the University of New Hampshire!

selected publications

RLC
ROIL: Robust Offline Imitation Learning

Gersi Doko, Guang Yang, Daniel Brown, and 1 more author

Reinforcement Learning Journal, May 2024

Abs Bib PDF

We study the problem of imitation learning via inverse reinforcement learning where the agent attempts to learn an expert’s policy from a dataset of collected state, action tuples. We derive a new Robust model-based Offline Imitation Learning method (ROIL) that mitigates covariate shift by avoiding estimating the expert’s occupancy frequency. Frequently in offline settings, there is insufficient data to reliably estimate the expert’s occupancy frequency and this leads to models that do not generalize well. Our proposed approach, ROIL, is a method that is guaranteed to recover the expert’s occupancy frequency and is efficiently solvable as an LP. We demonstrate ROIL’s ability to achieve minimal regret in large environments under covariate shift, such as when the state visitation frequency of the demonstrations does not come from the expert.
@article{roil, title = {ROIL: Robust Offline Imitation Learning}, author = {Doko, Gersi and Yang, Guang and Brown, Daniel and Petrik, Marek}, year = {2024}, month = may, institution = {RLC}, journal = {Reinforcement Learning Journal}, publisher = {RLJ}, volume = {1}, number = {1} }
NeurIPS

Risk-Averse Total-Reward Reinforcement Learning

Xihong Su, Jia Lin Hau, Gersi Doko, and 2 more authors

May 2025

RCR

Deep Reinforcement Learning based Optimization of an Island Energy-Water Microgrid System

Roozbeh Ghasemi, Gersi Doko, Marek Petrik, and 4 more authors

Resources, Conservation and Recycling, Oct 2024

Bib PDF

@article{deeprl-island,
  title = {Deep Reinforcement Learning based Optimization of an Island
             Energy-Water Microgrid System},
  author = {Ghasemi, Roozbeh and Doko, Gersi and Petrik, Marek and Wosnik, Martin and Lu, Zhongming and Foster, Diane and Mo, Weiwei},
  year = {2024},
  month = oct,
  journal = {Resources, Conservation and Recycling},
  publisher = {RCR},
  volume = {1},
  number = {1}
}