Jerin Paul Selvan

About

Jerin Paul Selvan is a researcher at the intersection of artificial intelligence, reinforcement learning, and evolutionary algorithms. His work focuses on developing autonomous agents capable of mastering complex tasks through minimal human intervention. In his most-cited paper, "Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning" (2022), Selvan demonstrates a novel approach to creating self-learning game-playing agents by combining NeuroEvolution of Augmenting Topologies (NEAT) with reinforcement learning techniques. This work addresses a critical challenge in AI research: the need for efficient, scalable testing environments for pathfinding and optimization algorithms. By enabling agents to play indefinitely without manual tuning, Selvan's methodology offers a robust framework for evaluating search space optimization in dynamic environments. His contributions have practical implications for robotics, autonomous systems, and simulation-based testing, where continuous learning and adaptation are essential. With growing interest in his research, Selvan is establishing himself as an emerging voice in the field of evolutionary reinforcement learning, pushing the boundaries of how artificial agents learn and interact with their environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

   2 citations · 2022

Key Collaborators

Contact & Links