On the grid-sampling limit SDE

In our recent work [3] we introduced the grid-sampling SDE as a proxy for modeling exploration in continuous-time reinforcement learning. In this note, we provide further motivation for the use of this SDE and discuss its wellposedness in the presence of jumps.

stat.ML cs.LG math.PR Bayesian Methods and Mixture Models Advanced Clustering Algorithms Research Simulation Techniques and Applications

View graph Source

Paper

Similar papers

A random measure approach to reinforcement learning in continuous timeChristian Bender, Nguyen Tran Thuan2024 · arXiv (Cornell University) · 1 citation In Library

Continuous time reinforcement learning: A random measure approachChristian Bender, Nguyen Tran Thuan2025 · Stochastic Processes and their Applications In Library

Robust and Scalable SDE Learning: A Functional PerspectiveS. Cameron, Tyron Cameron, Arnu Pretorius et al.2021 · International Conference on Learning Representations · 3 citations In Library

Smooth Exploration for Robotic Reinforcement LearningAntonin Raffin, Jens Kober, Freek Stulp2020 · elib (German Aerospace Center) · 88 citations In Library

Stochastic Differential Equations models for Least-Squares Stochastic Gradient DescentAdrien Schertzer, Loucas Pillaud-Vivien2024 · arXiv.org · 2 citations In Library

Elucidating the solution space of extended reverse-time SDE for diffusion modelsQinpeng Cui, Xinyi Zhang, Bao, Qiqi et al.2023 · arXiv (Cornell University) · 8 citations In Library

Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin DynamicsHaoyang Zheng, Hengrong Du, Qi Feng et al.2024 · International Conference on Machine Learning · 9 citations In Library

Exact Gibbs sampling for stochastic differential equations with gradient drift and constant diffusionXinyi Pei, Minhyeok Kim, Vinayak Rao2026 · Open MIND In Library

Efficient and Accurate Gradients for Neural SDEsPatrick Kidger, James Foster, Xuechen Li et al.2021 · Neural Information Processing Systems · 102 citations In Library

Efficient Exploration in Continuous-time Model-based Reinforcement LearningLenart Treven, Jonas Hübotter, Bhavya Sukhija et al.2023 · arXiv (Cornell University) · 22 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal