Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
This work addresses the problem of handling stochasticity and partial observability in reinforcement learning for continuous-control tasks, offering incremental improvements in sample efficiency and adaptation.
The paper tackled modeling stochastic dynamics in model-based reinforcement learning by using neural ODEs and SDEs, showing that neural SDEs capture stochasticity better and enable high-performing policies with improved sample efficiency, and introducing a latent SDE model that outperforms or matches other approaches on benchmarks.
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 action-conditional latent SDEs for RL planning in environments with stochastic transitions. Our code is available at: https://github.com/ChaoHan-UoS/NeuralRL