Browser opponent: alpha-beta minimax.
A few things
I’ve taught
machines.
I’m Sepehr. I build and study learning systems,
from game-playing agents to medical imaging.

01 / Selected work
Things I’ve built.
Some serious questions.
A little room to play.

VODLens CS2
Learn from
the replay.
Comparable pro plays. Video evidence attached.
Algorithmic pricing
When rivals
get along.
Learning to compete. Learning what a detector misses.
88.7%
Mean time in range / virtual adults
¹ Receives meal information unavailable to PPO.
AutoDoseRL
Learning to
stay in range.
A dosing policy with explicit safeguards.
A couple more questions
05—0605 / Visual robustness
A change of scenery.


Turn it up45%
An image transformation to try. The study compared three training recipes across 50 conditions.
See what held up06 / Poker & detectability
The price of
a poker face.
Mixed honest agents
Selfish CFR agents
Same detector family. Different definitions of honest. Best-found values in chips per hand.
See what stays hidden02 / About
The human bit.
I started with olympiad problems.
Now the experiments run in Python.
My background is in computer science at Western University. My work spans learning agents, medical imaging, retrieval, and game theory.
B.Sc. Honours Specialization in Computer Science
Western University · 2026
Apr 2026 — Present
Research Assistant
Still investigatingCognitive Development and Neuroimaging Laboratory
Western University
Developing computational tools for neuroimaging research. One of my early projects was an automated MRI segmentation pipeline.
2020 — 2024
Mathematics & CS Tutor
Self-employed · Iran & Canada
Olympiad combinatorics and geometry. University calculus, linear algebra, and computer science.
A few things along the way
Major average
Overall average
Dean’s Honor List
Western Admission Scholarship
Silver medalIranian National Mathematical Olympiad
Bronze medalIranian National Mathematical Olympiad
Third prizeEuropean Mathematical Cup
Usually within reach
Vision
PyTorch
CNNs & segmentation
Robustness evaluation
Learning agents
PPO · DQN · Q-learning
Stable-Baselines3
Gymnasium
Retrieval
FAISS
DuckDB · Polars
Ranking & LLM evaluation
Systems
Python · C/C++
Parallel simulation
Git · Linux