An information based approach to stochastic control problems
From MaRDI portal
Publication:2019688
DOI10.34768/AMCS-2020-0002zbMATH Open1461.93482arXiv1904.06287OpenAlexW3046208901MaRDI QIDQ2019688FDOQ2019688
Authors: Piotr Bania 
Publication date: 22 April 2021
Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)
Abstract: An information based method for solving stochastic control problems with partial observation has been proposed. First, the information-theoretic lower bounds of the cost function has been analysed. It has been shown, under rather weak assumptions, that reduction of the expected cost with closed-loop control compared to the best open-loop strategy is upper bounded by non-decreasing function of mutual information between control variables and the state trajectory. On the basis of this result, an Information Based Control method has been developed. The main idea of the IBC consists in replacing the original control task by a sequence of control problems that are relatively easy to solve and such that information about the state of the system is actively generated. Two examples of the operation of the IBC are given. It has been shown that the IBC is able to find the optimal solution without using dynamic programming at least in these examples. Hence the computational complexity of the IBC is substantially smaller than complexity of dynamic programming, which is the main advantage of the proposed method.
Full work available at URL: https://arxiv.org/abs/1904.06287
Recommendations
- Example for equivalence of dual and information-based optimal control
- Control and stabilization with insufficient information
- A forward method for optimal stochastic nonlinear and adaptive control
- Incremental value of information for discrete-time partially observed stochastic systems
- The information path functional approach to solution of a controllable stochastic problem
Measures of information, entropy (94A17) Feedback control (93B52) Stochastic systems in control theory (general) (93E03)
Cites Work
- Elements of Information Theory
- A stochastic quasi-Newton method for large-scale optimization
- Optimal Measurement Methods for Distributed Parameter System Identification
- Nonlinear Bayesian estimation using Gaussian sum approximations
- Control Under Communication Constraints
- Estimation of entropy and other functionals of a multivariate density
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Role of mutual information in entropy production under information exchanges
- Adaptive dual control. Theory and applications.
- Point-based value iteration for continuous POMDPs
- Information and entropy flow in the Kalman-Bucy filter
- Bayesian filtering and smoothing
- Title not available (Why is that?)
- Partial synchronization in stochastic dynamical networks with switching communication channels
- Discrete-time entropy formulation of optimal and adaptive control problems
- An active exploration method for data efficient reinforcement learning
- Entropy formulation of optimal and adaptive control
Cited In (10)
- Title not available (Why is that?)
- Asymmetric information control for stochastic systems with different intermittent observations
- On the choice of the cost function for nonlinear model predictive control: a multi-criteria evaluation
- Information-theoretic lower bounds of the quadratic cost in stochastic control with partial observation
- Optimal Control for Stochastic Systems With Multiple Controllers of Different Information Structures
- Solution to the variation problem for information path functional of a controlled random process
- Information Relaxation and Dual Formulation of Controlled Markov Diffusions
- Mean field approach to stochastic control with partial information
- Title not available (Why is that?)
- Reduction of future information required for optimal control of dynamic systems: a pseudostochastic model
This page was built for publication: An information based approach to stochastic control problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2019688)
