Results 1 to 10 of about 16,838,741 (322)
Forward-Backward Sweep Method for the System of HJB-FP Equations in Memory-Limited Partially Observable Stochastic Control [PDF]
Entropy, 2023 Memory-limited partially observable stochastic control (ML-POSC) is the stochastic optimal control problem under incomplete information and memory limitation.
Takehiro Tottori, Tetsuya J. Kobayashi
doaj +2 more sources
Memory-Limited Partially Observable Stochastic Control and Its Mean-Field Control Approach [PDF]
Entropy, 2022 Control problems with incomplete information and memory limitation appear in many practical situations. Although partially observable stochastic control (POSC) is a conventional theoretical framework that considers the optimal control problem with ...
Takehiro Tottori, Tetsuya J. Kobayashi
doaj +2 more sources
Stochastic control and non-equilibrium thermodynamics: fundamental limits. [PDF]
IEEE Trans Automat Contr, 2020 We consider damped stochastic systems in a controlled (time varying) potential and study their transition between specified Gibbs-equilibria states in finite time.
Chen Y, Georgiou T, Tannenbaum A.
europepmc +3 more sources
Neural Stochastic Control [PDF]
Neural Information Processing Systems, 2022 Control problems are always challenging since they arise from the real-world systems where stochasticity and randomness are of ubiquitous presence. This naturally and urgently calls for developing efficient neural control policies for stabilizing not only the deterministic equations but the stochastic systems as well.
Zhang, Jingdong, Zhu, Qunxi, Lin, Wei
openaire +3 more sources
Modeling Financial System with Interbank Flows, Borrowing, and Investing [PDF]
Risks, 2018 In our model, private actors with interbank cash flows similar to, but more general than that by Carmona et al. (2013) borrow from the non-banking financial sector at a certain interest rate, controlled by the central bank, and invest in risky assets ...
Aditya Maheshwari, Andrey Sarantsev
doaj +4 more sources
Recent Developments in Machine Learning Methods for Stochastic Control and Games [PDF]
arXiv.org, 2023 Stochastic optimal control and games have a wide range of applications, from finance and economics to social sciences, robotics, and energy management. Many real-world applications involve complex models that have driven the development of sophisticated ...
Ruimeng Hu, M. Laurière
semanticscholar +1 more source
Stability Verification in Stochastic Control Systems via Neural Network Supermartingales [PDF]
AAAI Conference on Artificial Intelligence, 2021 We consider the problem of formally verifying almost-sure (a.s.) asymptotic stability in discrete-time nonlinear stochastic control systems. While verifying stability in deterministic control systems is extensively studied in the literature, verifying ...
Mathias Lechner +3 more
semanticscholar +1 more source
Safety-Critical Control of Stochastic Systems using Stochastic Control Barrier Functions [PDF]
IEEE Conference on Decision and Control, 2021 Control barrier functions have been widely used for synthesizing safety-critical controls, often via solving quadratic programs. However, the existence of Gaussian-type noise may lead to unsafe actions and result in severe consequences. In this paper, we
Chuanzhen Wang +3 more
semanticscholar +1 more source
A Modified MSA for Stochastic Control Problems [PDF]
Applied Mathematics and Optimization, 2020 The classical Method of Successive Approximations (MSA) is an iterative method for solving stochastic control problems and is derived from Pontryagin’s optimality principle. It is known that the MSA may fail to converge.
B. Kerimkulov, D. vSivska, L. Szpruch
semanticscholar +1 more source
Gradient Flows for Regularized Stochastic Control Problems [PDF]
SIAM Journal of Control and Optimization, 2020 This work is motivated by a desire to extend the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used in the reinforcement learning community to solve control problems.
D. Šiška, Lukasz Szpruch
semanticscholar +1 more source