About

I’m a Mechatronics Engineer; graduated from the Mechatronics Engineering Department at Tishreen University back in 2022, where I focused primarily on Deep Reinforcement Learning under the supervision of Doctor Iyad Hatem. Previously, I worked as a Research Assistant at the Robotics Club of Tishreen University under the guidance of Doctor Essa Alghannam, where I worked on time series and computer vision research. In 2023, I became a Teaching Assistant for CS courses at the Mechatronics Department.

I’m broadly interested in Computer Science Research and currently applying for a Ph.D. degree in Computer Science in the U.S., focusing primarily on AI. Additionally, I take a keen interest in Reinforcement Learning, Statistical RL, and Deep RL. My research goal is to see complex, human-like behavior emerge from unsupervised interaction between groups of learning agents with an application’s focus on game theory, and techniques for decision-making (planning and learning) that enable single-situated agents and teams of agents to act intelligently in their environments and exhibit goal-directed behavior in real-time. Concretely this leads to a lot of questions I’m currently interested in:

• How can we use RL to design models of human agents? How can we ensure that RL-designed agents are human-compatible?
• How can we synthesize environments that push and test the capabilities of our agents?
• What algorithmic advances and software tools are needed to address these questions?
  

In practice this means working on understanding how to push the state of the art in multi-agent RL algorithms, designing new data-driven simulators, and trying to deploy simulator-designed controllers into real-world systems.

I’m also interested in state-of-the-art RL and NLP integration Research, including:

• RL for generative models, e.g., fine-tune LLMs with RL, The Transformer RL, and the IL library.
• Algorithmic and theoretical foundations of RLHF, e.g., offline RLHF, contextual dueling bandits with active query.
• RL with offline and online data, e.g., hybridRL.
• Representation learning in RL, e.g., theory of representation learning in RL, and theory of representation transfer in RL.
• Learning in partially observable systems, e.g., PAC RL w/ general function approximation in POMDPs and PSRs.