Kavosh Asadi
| Home | About me | Other Interests |
Welcome to my homepage!
I am an AI scientist whose career goal is to understand computational principles underlying intelligence. More specifically, I study agents that interact with a sequential environment to improve their behavior through trial and error. This agent-environment interaction is referred to as the reinforcement learning problem.
I have a PhD and an extensive background in the theoretical and empirical foundations of reinforcement learning. I have published more than a dozen papers at top-tier AI conferences such as Neurips, ICML, ICLR, AAAI, and ACL. On the academic side, I am really interested in understanding the optimization problem that arises in the context of learning the value function. On the aplication side, I am quite interested in the developing assistive AI agents that interact with humans and learn from feedback to provide better service. My aspiration is to make AI agents that co-exist with and help us live our best lives.
The best way to reach me for career-related stuff is by shooting me an email at my first name @alumni.brown.edu. I am genuinely interested in forming meaningful connections with fellow AI scientists, engineers, students, etc, so feel free to reach out even if we never met in person.
News
- Our paper on Fairness in Reinforcement Learning is accepted at RLC, the first instance of the Reinforcement Learning Conference. Super Excited to meet our wonderful community in Amherst!
- Our paper on learning the target network in function space got into ICML 2024. I am super excited about this one, so please stay tuned!
- Our paper on foundation models for continual learning was accepted at ICLR 2024.
- Will present two papers at Neurips 2023. (See you again in New Orleans!)
- Gave a talk at Seattle Mind and Machines meetup on UW’s beautiful campus.
- Gave a talk at Amazon’s RL reading group.
- Moved from Oahu, Hawaii to Seattle, WA.
- One paper accepted at AISTATS 2022.
- Coauthered the RL chapter of the D2L book.
- Two papers accepted at Neurips 2022.
- Gave a guest lecture at Harvard’s ML class.
- Moved from SF bay area to WFHH (Work From Home in Hawaii)
- One paper accepted at Neurips 2021.
- Two papers accepted at AAAI 2021.
- Moved from Providence, RI to SF bay area.
Affiliation
- 2020-Now: Applied Scientist at Amazon
- 2015-2020: PhD Student at Brown University
(Advisor: Michael Littman) - 2013-2015: Master’s Student at the University of Alberta
(Advisor: Rich Sutton) - 2008-2013: Undergraduate student at the University of Tehran
