Fahimeh Farahnakian

About

Fahimeh Farahnakian’s research lies at the intersection of multi-agent systems, machine learning, and robotics, with a particular focus on simulated soccer environments. Her work addresses the fundamental challenge of enabling autonomous agents to make intelligent decisions in real-time, dynamic, and noisy settings. She has made significant contributions to feature selection, demonstrating how removing irrelevant data can dramatically improve the performance of learning algorithms in complex multi-agent systems. Her 2009 paper on evaluating feature selection techniques in simulated soccer has garnered 7 citations, establishing a foundation for subsequent work in data preprocessing for robotics. Farahnakian has also advanced the application of decision tree learning and reinforcement learning in multi-agent contexts, showing how these methods can handle the inherent complexity of collaborative and adversarial environments. Her 2008 and 2009 papers on decision trees and reinforcement learning, each with 2 citations, provide practical frameworks for agent decision-making under uncertainty. Through her research, Farahnakian has helped bridge the gap between theoretical machine learning and real-world robotic applications, offering valuable insights for researchers developing intelligent systems that must operate in unpredictable conditions.

Research Focus

Key Achievements

Top Papers

1. 1
   Evaluating Feature Selection Techniques in Simulated Soccer Multi Agents System

   7 citations · 2009
2. 2
   Learning through Decision Tree in Simulated Soccer Environment

   2 citations · 2008
3. 3
   Reinforcement Learning for Soccer Multi-agents System

   2 citations · 2009

Key Collaborators

Contact & Links