Omid Saremi
Papers
1
Total Citations
8
H-Index
1
About
Omid Saremi is a researcher in robotics and computational intelligence, with a primary focus on reinforcement learning and adaptive control systems for autonomous locomotion. His most notable contribution is the development of the eXtended Classifier System for Real-time-input Real-time-output (XCSRR), a revised reinforcement learning framework designed to handle fully real-valued environments. This work, published in 2015, addresses the stability control of biped robots—a notoriously complex problem due to continuous state and action spaces. By enabling real-value input and output processing, Saremi’s XCSRR controller represents a significant step forward in bridging learning classifier systems with practical robotic applications. Although his most-cited paper has garnered 8 citations, its impact lies in laying groundwork for adaptive control in dynamic, real-world settings. Saremi’s research sits at the intersection of machine learning and biomechanical engineering, offering insights into how autonomous systems can learn to maintain balance and navigate uncertain terrains. His work is particularly valuable for students and researchers exploring reinforcement learning in continuous domains or seeking to apply evolutionary computation to robotic stability challenges.
Research Focus
Key Achievements
Top Papers
- 1