Hi! My name is Hamid Osooli, and I’m a PhD student in the Lab for Intelligent Robots and Agents (LIRA) at the University of Illinois Urbana-Champaign (UIUC), advised by Huy Tran. I’m excited about multi-agent coordination and planning for the teams of agents/robots. My work seeks to address the coordination issue in multi-agent reinforcement learning using tools such as game theory, mechanism design, and credit assignment. More specifically, I employ these tools to give the robots (or different parts within a robot!) the ability to coordinate in a cooperative task, or when facing an adversary.

For the summer and fall of 2025, I'm also working as a research intern at InstaDeep, where I focus on using reinforcement learning to address the weak-to-strong alignment problem in large language models (LLMs). This experience expands my research interests beyond robotics, allowing me to apply multi-agent coordination and RL principles to challenges in AI alignment.

Previously, I worked at the Persistent Autonomy and Robot Learning (PeARL) lab and New England Robotics Experimentation and Validation (NERVE) center at UMass Lowell (UML), advised by Reza Azadeh. My work there spanned different areas of robotics and learning, including multi-agent deep reinforcement learning, optimization and planning, machine learning modeling and sensor fusion, and robot design.

At UML I also joined the University Choir group and had the chance to perform with Cambridge Symphony Orchestra and Nashoba Valley Chorale at MIT Kresge Auditorium. If I’m not singing while playing with robots, I’m an avid hiker, and I enjoy fitness exercise, ice cream, and cooking.