2 papers
cs.LG2025
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
Tung Minh Luu, Younghwan Lee, Donghoon Lee +3
Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from…
quant-ph2024
Generalized wave-particle-Mixdness triality for n-path interferometers
Y. T. Tsui, Sunho Kim
The wave-particle duality, as one of the expressions of Bohr complementarity, is usually quantified by path predictability and the visibility of interference fringes. With the deve…