Achintha Wijesinghe

Papers

Total Citations

H-Index

About

Achintha Wijesinghe is a researcher whose work lies at the intersection of artificial intelligence, reinforcement learning, and game theory, with a particular focus on developing intelligent agents for complex, real-world environments. His primary research area addresses the challenge of training AI systems for stochastic, physics-based games—a domain far more unpredictable than classic board games like Chess or Go. In his most cited work, "Towards a Smart Opponent for Board Games: Learning beyond Simulations" (2020), Wijesinghe explores how reinforcement learning algorithms can be adapted for cue sport-based games such as Carrom, where real-world factors like friction and unpredictable collisions introduce significant complexity. This contribution highlights his broader interest in bridging the gap between simulated training environments and real-world application, a critical step for advancing robotics and autonomous systems. While his citation count is still growing, Wijesinghe’s work is notable for pushing the boundaries of AI beyond perfect-information games, offering insights into how agents can learn robust strategies in noisy, dynamic settings. His research is particularly valuable for students and researchers interested in the practical deployment of reinforcement learning in physical systems.