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 …
[图书][B] Neural approximations for optimal control and decision
Many scientific and technological areas of major interest require one to solve infinite-
dimensional optimization problems, also called functional optimization problems. In such a …
dimensional optimization problems, also called functional optimization problems. In such a …
A universal dynamic program and refined existence results for decentralized stochastic control
S Yüksel - SIAM Journal on Control and Optimization, 2020 - SIAM
For sequential stochastic control problems with standard Borel measurement and control
action spaces, we introduce a general (universally applicable) dynamic programming …
action spaces, we introduce a general (universally applicable) dynamic programming …
[图书][B] Finite Approximations in discrete-time stochastic control
Control and optimization of dynamical systems in the presence of stochastic uncertainty is a
mature field with a large range of applications. A comprehensive treatment of such problems …
mature field with a large range of applications. A comprehensive treatment of such problems …
Isomorphism properties of optimality and equilibrium solutions under equivalent information structure transformations: Stochastic dynamic games and teams
Static reduction of information structures is a method that is commonly adopted in stochastic
control, team theory, and game theory. One approach entails change of measure arguments …
control, team theory, and game theory. One approach entails change of measure arguments …
Controlled diffusions under full, partial and decentralized information: Existence of optimal policies and discrete-time approximations
We present existence and discrete-time approximation results on optimal control policies for
continuous-time stochastic control problems under a variety of information structures. These …
continuous-time stochastic control problems under a variety of information structures. These …
[图书][B] Control and system theory of discrete-time stochastic systems
JH van Schuppen - 2021 - Springer
Researchers and students who want to learn about control and system theory of discrete-
time stochastic systems at the master level or the Ph. D. level in engineering or in applied …
time stochastic systems at the master level or the Ph. D. level in engineering or in applied …
Decentralized multi-agent reinforcement learning for continuous-space stochastic games
A Altabaa, B Yongacoglu… - 2023 American Control …, 2023 - ieeexplore.ieee.org
Stochastic games are a popular framework for studying multi-agent reinforcement learning
(MARL). Recent advances in MARL have focused primarily on games with finitely many …
(MARL). Recent advances in MARL have focused primarily on games with finitely many …
Power-Estimation Trade-off of Vector-valued Witsenhausen Counterexample with Causal Decoder
M Le Treust, TJ Oechtering - IEEE Transactions on Information …, 2024 - ieeexplore.ieee.org
The vector-valued extension of the famous Witsenhausen counterexample setup is studied
where the encoder, ie the first decision maker, non-causally knows and encodes the iid state …
where the encoder, ie the first decision maker, non-causally knows and encodes the iid state …
Sequential Stochastic Control (Single or Multi-Agent) Problems Nearly Admit Change of Measures with Independent Measurement
I Hogeboom-Burr, S Yüksel - Applied Mathematics & Optimization, 2023 - Springer
Change of measures has been an effective method in stochastic control and analysis; in
continuous-time control this follows Girsanov's theorem applied to both fully observed and …
continuous-time control this follows Girsanov's theorem applied to both fully observed and …