I am a Senior Reinforcement Learning Engineer at Quilter, working on reinforcement learning for automated PCB design. I completed my PhD in Computer Science from the University of California, Irvine. My work lies at the intersection of multi-agent reinforcement learning, game theory, and optimization.

In reverse chronological order, I have worked on:

• Reinforcement Learning for LLM Hallucination Control at Qualcomm
• Reinforcement Learning for In-Context Learning at Microsoft Research as an RLOS participant
• Multi-Agent Reinforcement Learning at Zebra Technologies with Biswa Sengupta.
• Privacy-Preserving Reinforcement learning at the UCI Networking Group.
• Reinforcement Learning for Industrial Power Control, advised by Qiuhua Huang at the Pacific Northwest National Laboratory
• Music information retrieval algorithms at the Language & Speech Processing Institute of the Athena Research and Innovation Center.

I also hold a MS in Computer Engineering from the University of California, Irvine, and a MEng Diploma in EECS from the National Technical University of Athens. For more information about me, see my CV or contact me.

My origin is from Rethymno and I grew up in Athens, Greece. If you’d like to visit Crete, ask me for recommendations!

News

• April 2023 - Thrilled to announce my recent acceptance at the Microsoft Reinforcement Learning Open Source Festival 2023, exploring feature generation using transformers! Check out my screening exercise implementation conducting an inverted pole balancing task via transformers and reinforcement learning.

• March 2023 - Happy to announce I will be joining Qualcomm AI this summer, focusing on machine learning and combinatorial optimization under constraints.

• February 2023 - Our paper entitled Efficiently Computing Nash Equilibria in Adversarial Team Markov Games got accepted at ICLR 2023 as a notable-top-5% paper.

• January 2023 - Our paper entitled adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems got accepted at IoTDI 2023.

• September 2022 - Our paper entitled On Scrambling Phenomena for Randomly Initialized Recurrent Networks got accepted at NeurIPS 2022.

• June 2022 - Joined the Core ML team of Zebra Technologies as a Reinforcement Learning Engineer to work on multi-agent orchestration solutions with Jay Williams.

• June 2022 - Submitted my MS thesis entitled “Computing Nash Equilibria in Adversarial Stochastic Team Games”. Code containing algorithm implementation and multi-agent reinforcement learning environment can be found here.

• May 2022 - Participated in the Learning and Games program at the Simons Institute for the Theory of Computing. Particularly enjoyed the Multi-Agent Reinforcement Learning and Bandit Learning Workshop.

• March 2022 - Our paper entitled Reinforcement Learning for Location-Aware Scheduling got accepted at the inaugural ICLR 2022 Workshop on Generalizable Policy Learning in Physical World.

• July 2021 - Completed the Reinforcement Learning Specialization offered by the University of Alberta. This was probably one of the most organized and well-crafted courses I have ever taken.