Path Integral Control and State Dependent Feedback

Abstract

In this paper we address the problem to compute state dependent feedback controls for path integral control problems. To this end we generalize the path integral control formula and utilize this to construct parameterized state dependent feedback controllers. In addition, we show a novel relation between control and importance sampling: better control, in terms of control cost, yields more efficient importance sampling, in terms of effective sample size. The optimal control provides a zero-variance estimate.

Cited by in corpus (22)

• Adaptive importance sampling for control and inference
• A geometric approach to optimal nonequilibrium control: Minimizing dissipation in nanomagnetic spin systems
• Model Predictive Path Integral Control using Covariance Variable Importance Sampling
• Near-optimal protocols in complex nonequilibrium transformations
• Reinforcement learning of rare diffusive dynamics
• Controlled Sequential Monte Carlo
• Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother
• Deep Value Model Predictive Control
• Real-Time Stochastic Optimal Control for Multi-agent Quadrotor Systems
• Approximate Inference-based Motion Planning by Learning and Exploiting Low-Dimensional Latent Variable Models
• Sample Efficient Path Integral Control under Uncertainty
• Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
• Topology-Guided Path Integral Approach for Stochastic Optimal Control in Cluttered Environment
• Path Integral Sampler: a stochastic control approach for sampling
• Variational time reversal for free energy estimation in nonequilibrium steady states
• A Multilevel Approach for Stochastic Nonlinear Optimal Control
• Adaptive Smoothing Path Integral Control
• Connection among stochastic Hamilton-Jacobi-Bellman equation, path-integral, and Koopman operator on nonlinear stochastic optimal control
• Nonlinear stochastic receding horizon control: stability, robustness and Monte Carlo methods for control approximation
• Deterministic particle flows for constraining stochastic nonlinear systems
• An entropy penalized approach for stochastic control problems. Complete version
• A Topology-Guided Path Integral Approach for Stochastic Optimal Control