Muhamad Ridzuan Radin Muhamad Amin

About

Muhamad Ridzuan Radin Muhamad Amin is a researcher focused on the frontiers of deep reinforcement learning, with a particular emphasis on improving exploration strategies in complex decision-making systems. His most-cited work, "Re-exploration of ε-Greedy in Deep Reinforcement Learning" (2021), critically re-examines one of the field's foundational exploration methods, offering nuanced insights that challenge conventional assumptions and propose refinements for more efficient learning. This contribution, while still early in its citation trajectory, signals a rigorous approach to algorithmic optimization—a hallmark of his research. Amin’s work addresses the critical balance between exploration and exploitation, a core challenge in training autonomous agents. By dissecting and enhancing ε-greedy strategies, he provides practical pathways for more robust and sample-efficient reinforcement learning models. His research holds promise for applications ranging from robotics to game AI, where adaptive decision-making is paramount. As his citation count grows, Amin’s contributions are poised to influence both theoretical understanding and practical implementations in the rapidly evolving landscape of deep reinforcement learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Re-exploration of ε-Greedy in Deep Reinforcement Learning

   4 citations · 2021

Key Collaborators

Contact & Links