Tag
This paper proposes an entropy-regularized reinforcement learning approach to solve linear-quadratic Stackelberg differential games in regime-switching diffusion models, integrating neural networks to approximate value functions and escape suboptimal equilibria.
This paper introduces an entropy-regularized reinforcement learning framework for zero-sum stochastic differential games in regime-switching jump-diffusion processes, deriving HJBI equations and an actor-critic algorithm with applications to investment games.
This paper introduces regime-stratified evaluation for time series foundation models, revealing that aggregate metrics hide severe failures during traffic regime transitions, and proposes bimodal mixture augmentation to improve coverage while preserving overall accuracy.
This paper introduces a theoretical framework for quantifying deployment risk when training and deployment distributions differ due to latent regime dynamics modeled as a Markov-switching process, providing exact decomposition and finite-sample bounds.