[2603.23245] Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning

Computer Science > Machine Learning arXiv:2603.23245 (cs) [Submitted on 24 Mar 2026] Title:Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning Authors:Chao Han, Stefanos Ioannou, Luca Manneschi, T.J. Hayward, Michael Mangan, Aditya Gilra, Eleni Vasilaki View a PDF of the paper titled Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning, by Chao Han and 6 other authors View PDF HTML (experimental) Abstract: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 more effectively capture the inherent stochasticity of transition dynamics, enabling high-performing policies with improved sample efficiency in challenging scenarios. We leverage neural ODEs and SDEs for efficient policy adaptation to changes in environment dynamics via inverse models, requiring only limited interactions with the new environment. To address partial observability, we introduce a latent SDE model that combines an ODE with a GAN-trained stochastic component in latent space. Policies derived from this model provide a strong baseline, outperforming or matching general model-based and model-free approaches across stochastic continuous-control benchmarks. This work demonstrates the applicability of acti...