Reinforcement learning for near-optimal design of zero-delay codes for Markov sources
In the classical lossy source coding problem, one encodes long blocks of source symbols
that enables the distortion to approach the ultimate Shannon limit. Such a block-coding …
that enables the distortion to approach the ultimate Shannon limit. Such a block-coding …
Reinforcement learning for zero-delay coding over a noisy channel with feedback
In Shannon's classical information-theoretic lossy coding problem, one is allowed to encode
long sequences of source symbols at once in order to achieve a lower distortion, which is …
long sequences of source symbols at once in order to achieve a lower distortion, which is …
Average cost dynamic programming equations for controlled Markov chains with partial observations
VS Borkar - SIAM Journal on Control and Optimization, 2000 - SIAM
The value function for the average cost control of a class of partially observed Markov chains
is derived as the" vanishing discount limit," in a suitable sense, of the value functions for the …
is derived as the" vanishing discount limit," in a suitable sense, of the value functions for the …
On optimal causal coding of partially observed Markov sources in single and multiterminal settings
S Yuksel - IEEE Transactions on Information Theory, 2012 - ieeexplore.ieee.org
The optimal causal (zero-delay) coding of a partially observed Markov process is studied,
where the cost to be minimized is a bounded, nonnegative, additive, measurable single …
where the cost to be minimized is a bounded, nonnegative, additive, measurable single …
[HTML][HTML] A further remark on dynamic programming for partially observed Markov processes
VS Borkar, A Budhiraja - Stochastic processes and their applications, 2004 - Elsevier
In (Stochastic Process. Appl. 103 (2003) 293), a pair of dynamic programming inequalities
were derived for the 'separated'ergodic control problem for partially observed Markov …
were derived for the 'separated'ergodic control problem for partially observed Markov …
Whittle index for partially observed binary Markov decision processes
VS Borkar - IEEE Transactions on Automatic Control, 2017 - ieeexplore.ieee.org
We consider the problem of dynamically scheduling M out of N binary Markov chains when
only noisy observations of state are available, with ergodic (equivalently, long run average) …
only noisy observations of state are available, with ergodic (equivalently, long run average) …
Risk sensitive control of discrete time partially observed Markov processes with infinite horizon
GB Di Masi, L Sthttner - … : An International Journal of Probability and …, 1999 - Taylor & Francis
In this paper existence of solutions to the Bellman equation corresponding to risk sensitive
control of partially observed discrete time Markov processes is shown; this in turn leads to …
control of partially observed discrete time Markov processes is shown; this in turn leads to …
[PS][PS] Statistique asymptotique pour les modeles de Markov caché
L Mevel - Th ese de doctorat, universit e de Rennes, 1997 - idsa.prd.fr
Je voudrais exprimer ma gratitude a Jean Deshayes, pour avoir pr esid e le jury de cette th
ese, ainsi qu'a l'ensemble de l'equipe de probabilit es de l'universit e de Rennes, pour …
ese, ainsi qu'a l'ensemble de l'equipe de probabilit es de l'universit e de Rennes, pour …
Optimal Real-Time Coding and Control Under Information Constraints: Structural and Existence Results
Optimal Real-Time Coding and Control Under Information Constraints: Structural and Existence
Results | SpringerLink Skip to main content Advertisement SpringerLink Account Menu Find a …
Results | SpringerLink Skip to main content Advertisement SpringerLink Account Menu Find a …