Kasper Johansson
Papers
1
Total Citations
6
H-Index
1
About
Kasper Johansson is a rising researcher in the field of online learning and decision-making under uncertainty, with a primary focus on the multi-armed bandit (MAB) framework. His work bridges theoretical foundations and practical constraints, particularly in robotic applications where physical actions limit available choices. In his most cited paper, "Multi-armed Bandit Learning on a Graph" (2023, 6 citations), Johansson introduces a novel approach that models arm selection as a graph-based problem, capturing real-world dependencies between actions. This contribution is significant for advancing MAB theory in structured environments, offering new algorithms that balance exploration and exploitation under spatial or sequential constraints. While still early in his career, Johansson’s work demonstrates clear potential to impact fields like robotics, recommendation systems, and adaptive control. His research is characterized by a rigorous mathematical approach and a commitment to solving practical, constrained decision-making problems, making him a promising voice in the evolving landscape of bandit learning and its applications.
Research Focus
Key Achievements
Top Papers
- 1Multi-armed Bandit Learning on a Graph6 citations · 2023