Abrar Rahman
Papers
1
Total Citations
2
H-Index
1
About
Abrar Rahman is a researcher at the forefront of artificial intelligence, specializing in lifelong reinforcement learning and its application to complex, dynamic environments such as real-time strategy games. His most-cited work, "System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games" (2022), lays the architectural groundwork for creating AI agents that can continually adapt and improve without forgetting prior knowledge—a critical challenge for deploying autonomous systems in the real world. By integrating continual learning mechanisms directly into the agent's design, Rahman addresses the fundamental need for Artificial and Robotic Systems to evolve alongside shifting conditions, moving beyond static, one-shot training paradigms. Although his citation count is still growing, his contributions are pivotal for researchers aiming to build truly lifelong learning machines. His work stands as a foundational blueprint for those seeking to bridge the gap between theoretical continual learning and practical, deployable AI that can learn and adapt over extended lifetimes.
Research Focus
Key Achievements
Top Papers
- 1