4.8k citations · 5.1k across the 59 of their papers we have counts for
8 papers · 1 filter
Threshold Structure of Optimal Policies in Restart POMDPs
Konstantin Avrachenkov, Alexey Piunovskiy, Yi Zhang
We study a Restart POMDP (Partially Observable Markov Decision Process) on a general Borel state space, where the controller either lets the hidden state evolve unobserved or resta…
LP Based Upper and Lower Bounds for Cesàro and Abel Limits of the Optimal Values in Problems of Control of Stochastic Discrete Time Systems
Konstantin Avrachenkov, Vladimir Gaitsgory, Lucas Gamertsfelder
In this paper, we study asymptotic properties of problems of control of stochastic discrete time systems (also known as Markov decision processes) with time averaging and time disc…
Dynamic social learning under graph constraints
Konstantin Avrachenkov, Vivek S. Borkar, Sharayu Moharir +1
We introduce a model of graph-constrained dynamic choice with reinforcement modeled by positively -homogeneous rewards. We show that its empirical process, which can be written…
Linearly Convergent Asynchronous Distributed ADMM via Markov Sampling
Suhail M. Shah, Konstantin E. Avrachenkov
We consider the consensual distributed optimization problem and propose an asynchronous version of the Alternating Direction Method of Multipliers (ADMM) algorithm to solve it. The…
Impulsive Control for G-AIMD Dynamics with Relaxed and Hard Constraints
Konstantin Avrachenkov, Alexei Piunovskiy, Yi Zhang
Motivated by various applications from Internet congestion control to power control in smart grids and electric vehicle charging, we study Generalized Additive Increase Multiplicat…
Ordered field property for zero-sum stochastic games
K. Avrachenkov, V. Ejov, J. A. Filar +1
We consider a finite state, finite action, zero-sum stochastic games with data defining the game lying in the ordered field of algebraic numbers. In both the discounted and the lim…
Singularly perturbed linear programs and Markov decision processes
Konstantin Avrachenkov, Jerzy Filar, Vladimir Gaitsgory +1
Linear programming formulations for the discounted and long-run average MDPs have evolved along separate trajectories. In 2006, E. Altman conjectured that the two linear programmin…
Distributed Weight Selection in Consensus Protocols by Schatten Norm Minimization
Mahmoud El Chamie, Giovanni Neglia, Konstantin Avrachenkov
In average consensus protocols, nodes in a network perform an iterative weighted average of their estimates and those of their neighbors. The protocol converges to the average of i…