Deep reinforcement learning in finite-horizon to explore the most probable transition pathway

DOI10.1016/j.physd.2023.133955arXiv2304.12994MaRDI QIDQ6118140

No author found.

Publication date: 23 February 2024

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2304.12994

zbMATH Keywords

optimal controlreinforcement learningfinite-horizonOnsager-Machlup action functionalmost probable transition pathwayterminal prediction

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of optimal control and differential games (49N90) Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Onsager-Machlup function as Lagrangian for the most probable path of a diffusion process
• A distribution-free theory of nonparametric regression
• Nonparametric regression with additional measurement errors in the dependent variable
• Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications
• Data-driven method to learn the most probable transition pathway and stochastic differential equation
• Neural network stochastic differential equation models with applications to financial data forecasting
• Experimental Design for Biological Systems
• Robust shortest path planning and semicontractive dynamic programming
• Fluctuations and Irreversible Thermodynamics
• The geometric minimum action method: A least action principle on the space of curves
• PRICING OF HIGH-DIMENSIONAL AMERICAN OPTIONS BY NEURAL NETWORKS
• Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks
• Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning
• Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Convergence Analysis
• The Onsager–Machlup function as Lagrangian for the most probable path of a jump-diffusion process
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
• Dynamics and bistability in a reduced model of the lac operon
• Fluctuations and Irreversible Processes

This page was built for publication: Deep reinforcement learning in finite-horizon to explore the most probable transition pathway