Ehsan Futuhi

I am an AI researcher working on planning algorithms at the intersection of reinforcement learning, heuristic search, and foundation-model reasoning. I received my M.Sc. in Computing Science from the University of Alberta under the supervision of Prof. Martin Müller, where my research focused on improving the sample efficiency of policy-gradient algorithms in sparse-reward continuous control tasks through search and subgoal discovery.

I am currently a Data Scientist at MedWatch Technologies, where I work on AI methods for non-invasive blood glucose monitoring. I am also a part-time Research Assistant at the Moving AI Lab under the supervision of Prof. Nathan Sturtevant, where I study the planning and reasoning capabilities of large language models.

news

publications

Planning with Transformers: Chain of Computation and Structured Context Windows

Ehsan Futuhi, Nathan R. Sturtevant

arXiv preprint arXiv:2607.17710, 2026

2026

Learning Admissible Heuristics for A*: Theory and Practice

Ehsan Futuhi, Nathan R. Sturtevant

International Conference on Learning Representations (ICLR), 2026

2026

A Parallel CPU-GPU Framework for Batching Heuristic Operations in Depth-First Heuristic Search

Ehsan Futuhi, Nathan R. Sturtevant

AAAI Conference on Artificial Intelligence (AAAI), 2026 — Oral Presentation

2026

ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control

Ehsan Futuhi, Shayan Karimi, Chao Gao, Martin Müller

Transactions on Machine Learning Research (TMLR), 2025

2025

Improving Deep Deterministic Policy Gradient for Sparse Reward and Goal-Conditioned Continuous Control

Ehsan Futuhi

Master’s Thesis, University of Alberta, 2024

2024

On using Monte-Carlo Tree Search to Solve Puzzles

Mohammad Sina Kiarostami, Mohammadreza Daneshvaramoli, Saleh Khalaj Monfared, Aku Visuri, Helia Karisani, Simo Hosio, Hamed Khashehchi, Ehsan Futuhi, Dara Rahmati, Saeid Gorgin

International Conference on Computer Technology Applications, 2021

2021

On Distributed Algorithms for Minimum Dominating Set problem, from theory to application

Sharareh Alipour, Ehsan Futuhi, Shayan Karimi

arXiv preprint arXiv:2012.04883, 2020

2020

Solving Nurikabe with Monte-Carlo Tree Search

Ehsan Futuhi, Shayan Karimi

International Conference on Computational Intelligence and Applications (ICCIA), 2020

2020

service

  • Reviewer: ICLR, AAAI, ICAPS, UAI

skills

  • Python, JAX, Java, C/C++
  • PyTorch/LibTorch, TensorFlow, PDDL
  • LLM, VLM, VLA
  • GCP, AWS, Azure, Docker, Kubernetes