Mohammad Hasan Olyaei

About

Mohammad Hasan Olyaei is a researcher focused on reinforcement learning and adaptive decision-making in dynamic environments. His work centers on developing and testing algorithms that can navigate complex, changing scenarios, particularly in grid-world simulations. His most cited paper, "Implement Deep SARSA in Grid World with Changing Obstacles and Testing Against New Environment" (2018), demonstrates a key contribution: applying the Deep SARSA algorithm to environments with shifting obstacles, and rigorously evaluating its performance against novel, unseen conditions. This work highlights his interest in the robustness and generalization of reinforcement learning models—critical for real-world applications like robotics and autonomous navigation. While his citation count is modest, Olyaei’s research addresses a fundamental challenge in AI: creating agents that can adapt to unpredictable changes without retraining. His approach bridges theoretical algorithm design with practical testing, offering insights for students and researchers exploring how deep reinforcement learning can handle non-stationary environments. Olyaei’s work serves as a stepping stone for further studies in adaptive AI systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Implement Deep SARSA in Grid World with Changing Obstacles and Testing Against New Environment

   2 citations · 2018

Key Collaborators

Contact & Links