Adaptive importance sampling for control and inference

DOI10.1007/s10955-016-1446-7zbMath1338.93166arXiv1505.01874OpenAlexW1752690783WikidataQ59438775 ScholiaQ59438775MaRDI QIDQ290478

H. C. Ruiz, Hilbert J. Kappen

Publication date: 1 June 2016

Published in: Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1505.01874

Mathematics Subject Classification ID

Feedback control (93B52) Neural biology (92C20) Brownian motion (60J65) Dynamic programming (90C39) Optimal stochastic control (93E20) Hamilton-Jacobi equations (35F21)

Related Items (22)

Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space ⋮ Design of biased random walks on a graph with application to collaborative recommendation ⋮ Variational Inference for Stochastic Differential Equations ⋮ An estimator for the relative entropy rate of path measures for stochastic differential equations ⋮ Action selection in growing state spaces: control of network structure growth ⋮ Optimal control of probabilistic Boolean control networks: A scalable infinite horizon approach ⋮ Nonparametric inference of stochastic differential equations based on the relative entropy rate ⋮ Controlled sequential Monte Carlo ⋮ An Optimal Control Derivation of Nonlinear Smoothing Equations ⋮ Computable Primal and Dual Bounds for Stochastic Control ⋮ An iterative Bayesian filtering framework for fast and automated calibration of DEM models ⋮ Adaptive sampling of large deviations ⋮ Convergence rates for optimised adaptive importance samplers ⋮ Implicitly adaptive importance sampling ⋮ Variational approach to rare event simulation using least-squares regression ⋮ Data assimilation: The Schrödinger perspective ⋮ Learning effective state-feedback controllers through efficient multilevel importance samplers ⋮ Unnamed Item ⋮ Adaptive path-integral autoencoder: representation learning and planning for dynamical systems ⋮ A multilevel approach for stochastic nonlinear optimal control ⋮ Controlled interacting particle algorithms for simulation-based reinforcement learning ⋮ Iterative Path Integral Approach to Nonlinear Stochastic Optimal Control Under Compound Poisson Noise

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal control as a graphical model inference problem
• A Bayesian approach for inferring neuronal connectivity from calcium fluorescent imaging data
• Smoothing algorithms for state-space models
• Differential dynamic programming and Newton's method for discrete optimal control problems
• A tutorial on the cross-entropy method
• A solution of the smoothing problem for linear dynamic systems
• Backward Simulation Methods for Monte Carlo Statistical Inference
• Efficient computation of optimal actions
• Functional Approximations and Dynamic Programming
• On Transforming a Certain Class of Stochastic Processes by Absolutely Continuous Substitution of Measures
• Learning Tetris Using the Noisy Cross-Entropy Method
• A sequential smoothing algorithm with linear computational cost
• Optimal Control and Nonlinear Filtering for Nondegenerate Diffusion Processes
• Universal approximation bounds for superpositions of a sigmoidal function
• Variance Reduction for Simulated Diffusions
• An analysis of temporal-difference learning with function approximation
• Importance Sampling, Large Deviations, and Differential Games
• Applications of the Cross-Entropy Method to Importance Sampling and Optimal Control of Diffusions

This page was built for publication: Adaptive importance sampling for control and inference