AI and Optimization Group | Welcome

Pi Star AI and Optimization Lab


March-2022: Lab director Dr. Guni Sharon was awarded the "AI 2000 Most Influential Scholar Honorable Mention in AAAI/IJCAI" by ArnetMiner (AMiner).

August-2021: Lab director Dr. Guni Sharon will be providing an Early-Career Spotlight Invited talk during the 30th International Joint Conference on Artificial Intelligence (IJCAI-21). The talk titled "Alleviating Road Traffic Congestion with Artificial Intelligence" will be provided virtually on Aug 25th at 14:30 EDT.

March-2021: 5. Several news articles covered our research on self-optimizing signalized intersection controllers. These articles can be found on: FUTURITY KHOU-11, KBTX-TV, Настоящее Время Russian channel (our story starts on 16:25), and KAGS-TV.

August-2020: Lab members Dr. Guni Sharon recieved the journal of Artificial Intelligence (AIJ) 2020 Prominent Paper Award for the paper "Conflict Based Seach for Optimal Multi Agent Pathfinding".

June-2020: Lab members Sheelabhadra Dey and Sumedh Pendurkar won 1st place out of 15 submissions in the data science competition hosted by TAMIDS. The TAMIDS director wrote "The winning team derived novel insights into airline performance and translated these into recommendations for business operations."

October-2019: Our lab hosted students form James Madison High School, Houston. The visiting students were excited to learn about our research and participate in demonstrations of autonomous driving, and Intelligent traffic management.

October-2019: Group member Aaron Parks-Young is set to give a talk at INFORMS-19 covering his research on Autonomous Intersection Management.

September-2019: New PhD students join our lab, James Ault and Sheelabhadra Dey. Good Luck to both!


Pi Star is a research lab at the Computer Science & Engineering Department, Texas A&M University. Our research surrounds general artificial intelligence with a special focus on reinforcement learning and combinatorial and convex optimization.

Optimize your performance by following π*

Artificial Intelligence

Develop rational agents that learn, compute, and execute plans and policies in complex environments

Intelligent Transportation Systems

Apply theortical research in various transportation scenarios. Specifically we address applications such as autonomous driving, intersection management and control, flow optimization over road networks, and multiagent pathfinding

Machine Learning

Combine and develop latest image processing and reinforcement learning techniques for creating general and adaptive AI systems