Arash Bahari Kordabad

About

Arash Bahari Kordabad is a researcher at the forefront of safe and robust reinforcement learning (RL), with a focus on bridging control theory and machine learning. His key research areas include safe RL, stochastic and distributionally robust model predictive control (MPC), and chance-constrained optimization. In his highly cited 2022 work, "Safe Reinforcement Learning Using Wasserstein Distributionally Robust MPC and Chance Constraint," Bahari Kordabad addresses the critical challenge of ensuring safety in RL by integrating function approximators with Stochastic MPC and Distributionally Robust MPC. He innovatively employs Conditional Value at Risk (CVaR) to measure and manage probabilistic constraints, offering a principled framework for decision-making under uncertainty. This work, with 14 citations, has made a notable impact by providing a rigorous method to guarantee safety in complex, data-driven control systems. His contributions are particularly valuable for applications in autonomous systems and robotics, where reliability is paramount. Through his research, Bahari Kordabad is advancing the practical deployment of RL in safety-critical environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Safe Reinforcement Learning Using Wasserstein Distributionally Robust MPC and Chance Constraint

   14 citations · 2022

Key Collaborators

Contact & Links