Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning

ArXi:2603.23245v1 Announce Type: cross We investigate neural ordinary and stochastic differential equations (neural ODEs and SDEs) to model stochastic dynamics in fully and partially observed environments within a model-based reinforcement learning (RL) framework. Through a sequence of simulations, we show that neural SDEs effectively capture the inherent stochasticity of transition dynamics, enabling high-performing policies with improved sample efficiency in challenging scenarios.