Learning-based control: A tutorial and some recent results
This monograph presents a new framework for learning-based control synthesis of
continuous-time dynamical systems with unknown dynamics. The new design paradigm …
continuous-time dynamical systems with unknown dynamics. The new design paradigm …
Ergodic risk-sensitive control—a survey
A Biswas, VS Borkar - Annual Reviews in Control, 2023 - Elsevier
Risk-sensitive control has received considerable interest since the seminal work of Howard
and Matheson (Howard and Matheson, 1971/72) because of its ability to account for …
and Matheson (Howard and Matheson, 1971/72) because of its ability to account for …
[图书][B] Mathematical control theory for stochastic partial differential equations
Q Lü, X Zhang - 2021 - Springer
It is well-known that Control Theory was founded by N. Wiener in 1948 ([349]). After that, this
theory was greatly extended to various complicated setting and widely used in sciences and …
theory was greatly extended to various complicated setting and widely used in sciences and …
[图书][B] Fokker–Planck–Kolmogorov Equations
This book gives an exposition of the principal concepts and results related to second order
elliptic and parabolic equations for measures, the main examples of which are Fokker …
elliptic and parabolic equations for measures, the main examples of which are Fokker …
[图书][B] Representations of algebraic groups
JC Jantzen - 2003 - books.google.com
Now back in print by the AMS, this is a significantly revised edition of a book originally
published in 1987 by Academic Press. This book gives the reader an introduction to the …
published in 1987 by Academic Press. This book gives the reader an introduction to the …
Policy gradient and actor-critic learning in continuous time and space: Theory and algorithms
We study policy gradient (PG) for reinforcement learning in continuous time and space
under the regularized exploratory formulation developed by Wang et al.(2020). We …
under the regularized exploratory formulation developed by Wang et al.(2020). We …
Multi-UAV trajectory and power optimization for cached UAV wireless networks with energy and content recharging-demand driven deep learning approach
In this paper, we propose a novel joint trajectory and communication scheduling scheme for
multiple unmanned aerial vehicles (UAVs) enabled wireless caching networks. To exploit …
multiple unmanned aerial vehicles (UAVs) enabled wireless caching networks. To exploit …
Quasi-stationary distribution for strongly Feller Markov processes by Lyapunov functions and applications to hypoelliptic Hamiltonian systems
A Guillin, B Nectoux, L Wu - Journal of the European …, 2024 - content.ems.press
We establish a general result on the existence and uniqueness of a quasi-stationary
distribution D of a strongly Feller Markov process. Xt; t 0/killed when it exits a domain D …
distribution D of a strongly Feller Markov process. Xt; t 0/killed when it exits a domain D …
Geometry of information structures, strategic measures and associated stochastic control topologies
In many areas of applied mathematics, decentralization of information is a ubiquitous
attribute affecting how to approach a stochastic optimization, decision and estimation, or …
attribute affecting how to approach a stochastic optimization, decision and estimation, or …
A dynamical systems theory of thermodynamics
WM Haddad - 2019 - torrossa.com
Thermodynamics is a physical branch of science that governs the thermal behavior of
dynamical systems, from those as simple as refrigerators to those as complex as our …
dynamical systems, from those as simple as refrigerators to those as complex as our …