Author name: Daniel Bloch

Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS

Daniel Bloch / April 8, 2026

arXiv:2604.05008v1 Announce Type: new
Abstract: This paper introduces a novel generative framework for synthesising forward-looking, c\`adl\`ag stochastic trajectories that are sequentially consistent with time-evolving path-law proxies, thereby incor…

cs.LG, q-fin.MF, q-fin.PR, q-fin.ST

Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions

Daniel Bloch / April 7, 2026

arXiv:2604.04662v1 Announce Type: new
Abstract: This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement learning architectures, …