2 papers
stat.ML2026
Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS
Daniel Bloch
This paper introduces a novel generative framework for synthesising forward-looking, cà dlà g stochastic trajectories that are sequentially consistent with time-evolving path-law p…
cs.LG2026
Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions
Daniel Bloch
This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement l…