Bio

Reinforcement Learning enables agents to learn optimal behavior through interactions with the environment; it helps humans and animals rapidly adapt to new circumstances, and drives the emergence of complex learned behaviors. My research is focused on Reinforcement Learning—developing scalable and resilient algorithms that enable reliable decision-making in complex, single-situated, multi-agent, and distributed environments to see complex, human-like behavior emerge from unsupervised interaction with an application’s focus on game theory, and techniques for decision-making (planning and learning) that exhibit goal-directed behavior. I draw upon techniques from optimization, machine and deep learning, and statistics to tackle challenges at the intersection of theoretical foundations and practical deployment of RL. Concretely, this leads to a lot of questions I’m currently interested in: How can interaction lead to better behavior, better perception, better models of the world? How can we develop RL algorithms that can generalize to new situations and adapt to changing environments?

My research span several key areas:

• RL for/via Generative Models: Investigating RL integration with generative models to improve their performance, particularly in tasks where traditional training objectives like maximum likelihood estimation fall short in order to provide a framework for optimizing generative models based on complex, non-differentiable, or preference-driven objectives.
• Core RL Theory: Theoretical foundations of reinforcement learning (RL), especially in the function-approximation setting.
• RL with offline and online data: Sample-efficient reinforcement learning–algorithms and theories for learning near-optimal policies.
• Representation, Hierarchical RL, Risk-Averse, Open-Ended and Meta Learning in RL: Scalable frameworks for submodular maximization and adaptive meta-learning for discrete tasks, focusing on applications that demand large-scale processing and resilience to data uncertainty. I am also interested in the theory of representation learning and representation transfer in RL.
• Finance, Economics, and Game Theory: I view this as an integration, rather than an application. Specifically, multi-agent reinforcement learning (MARL), opponent modelling, game-theoretic Offline and adversarial RL, risk-aware and behavioral RL, and more recently algorithmic trading, optimal execution, and market impact and stochastic games—focusing on how adaptive, learning agents make sequential decisions in competitive, strategic, and uncertain environments.

Currently, I am a research assistant at the Max Blanck Institute for Cognitive and Brain Sciences, working with Dr. Nikola Milosevic and Prof. Charley Wu at the Machine and Human Cognition Lab. I am also a research collaborator at the Adaptive Systems Research Group at University of Hertfordshire, working on empowerment, information theory, and RL with Dr. Nicola Catenacci Volpi. Before that, I was a research intern at Max Planck Institute for Biological Cybernetics, where I worked with Dr. Andrew Webb and Prof. Peter Dayan at the Computational Neuroscience Lab. I completed my BSc degree in Mechatronics Engineering at Tishreen University in 2022.