Research
Generally, I am interested in designing intelligent systems, e.g. active agents, capable of high
real-world performance.
My current research area is Event-Based Vision, employing state-of-the-art Computer Vision, Deep
Learning, and Reinforcement Learning methods.
|
Publications and Pre-prints
|
Implicit Poisoning Attacks in Two-Agent Reinforcement Learning:
Adversarial Policies for Training-Time Attacks
Mohammad Mohammadi *,
Jonathan Nöther *,
Debmalya Mandal,
Adish Singla,
Goran Radanovic
AAMAS, 2023
In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker
implicitly poisons the effective environment of one of the agents by modifying the policy of its
peer.
|
PALMER: Perception-Action Loop with Memory for Long-Horizon
Planning
Onur Beker,
Mohammad Mohammadi,
Amir Zamir
NeurIPS, 2022
project page
We introduce PALMER, a long-horizon planning method that directly operates on high dimensional
sensory input observable by an agent on its own (e.g., images from an onboard camera).
|
More about me!
|
I'm a big fan of stand-up comedy (Dave Chappelle and Bill Burr are my all-time favorites). I'm
always up for exploring new cafes and trying out their lattes! In my free time, you can find me at
the gym, lost in a good book, or just hanging out with friends. I've got a soft spot for tennis,
and there's nothing like the joy of hiking in the great outdoors!
|
|