| Publication | Date of Publication | Type |
|---|
Strong and weak quantitative estimates in slow-fast diffusions using filtering techniques
SIAM Journal on Control and Optimization | 2026-08-28 | Paper |
A concentration bound for \(\mathrm{TD}(0)\) with function approximation
Stochastic Systems | 2026-08-05 | Paper |
Lagrangian index policy for restless bandits with average reward
Queueing Systems | 2026-03-30 | Paper |
An actor-critic algorithm with function approximation for risk sensitive cost Markov decision processes
IEEE Transactions on Automatic Control | 2026-03-17 | Paper |
Stochastic approximation and reinforcement learning: the interface and a little beyond
Statistical Science | 2026-02-10 | Paper |
A dynamic view of some anomalous phenomena in SGD for over-parametrized neural networks
Systems & Control Letters | 2025-12-15 | Paper |
Stochastic approximation in non-Markovian environments
Systems & Control Letters | 2025-10-29 | Paper |
Stochastic approximation with two time scales: the general case
Stochastic Processes and their Applications | 2025-10-29 | Paper |
The ODE method for asymptotic statistics in stochastic approximation and reinforcement learning
The Annals of Applied Probability | 2025-06-18 | Paper |
Some big issues with small noise limits in Markov decision processes
Systems & Control Letters | 2025-02-18 | Paper |
Controlled martingale problems and their Markov mimics
SIAM Journal on Control and Optimization | 2024-09-20 | Paper |
Reinforcement learning in non-Markovian environments
Systems & Control Letters | 2024-05-17 | Paper |
| Risk-sensitive control, single controller games and linear programming | 2023-10-26 | Paper |
Stochastic approximation. A dynamical systems viewpoint
Texts and Readings in Mathematics | 2023-09-04 | Paper |
In memoriam: Aristotle Arapostathis (1954--2021). Stochastic control and stability with applications
Systems & Control Letters | 2023-06-27 | Paper |
| Functional Central Limit Theorem for Two Timescale Stochastic Approximation | 2023-06-09 | Paper |
Elementary convexity with optimization
Texts and Readings in Mathematics | 2023-04-26 | Paper |
A selection procedure for extracting the unique Feller weak solution of degenerate diffusions
Applied Mathematics and Optimization | 2023-04-03 | Paper |
| Remarks on Differential Inclusion limits of Stochastic Approximation | 2023-03-08 | Paper |
Concentration of Contractive Stochastic Approximation and Reinforcement Learning
Stochastic Systems | 2023-01-23 | Paper |
A concentration bound for \(\operatorname{LSPE}( \lambda )\)
Systems & Control Letters | 2023-01-05 | Paper |
| Ergodic Risk-sensitive control -- A survey | 2022-12-31 | Paper |
Whittle indexability in egalitarian processor sharing systems
Annals of Operations Research | 2022-11-09 | Paper |
| A Concentration Bound for Distributed Stochastic Approximation | 2022-10-09 | Paper |
Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes
IEEE Transactions on Automatic Control | 2022-07-28 | Paper |
ERRATUM: LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The Nonergodic Case
SIAM Journal on Control and Optimization | 2022-05-03 | Paper |
Revisiting SIR in the age of COVID-19: explicit solutions and control problems
SIAM Journal on Control and Optimization | 2022-04-27 | Paper |
Whittle index based Q-learning for restless bandits with average reward
Automatica | 2022-03-18 | Paper |
Corrigendum to: ``A concentration bound for contractive stochastic approximation''
Systems & Control Letters | 2022-03-01 | Paper |
A selection procedure for extracting the unique Feller weak solution of degenerate diffusions
(available as arXiv preprint) | 2022-02-27 | Paper |
A concentration bound for contractive stochastic approximation
Systems & Control Letters | 2021-11-10 | Paper |
Prospect-theoretic Q-learning
Systems & Control Letters | 2021-11-10 | Paper |
Full gradient DQN reinforcement learning: a provably convergent scheme
Modern Trends in Controlled Stochastic Processes: | 2021-09-30 | Paper |
``Controlled'' versions of the Collatz-Wielandt and Donsker-Varadhan formulae
Infosys Science Foundation Series | 2021-08-31 | Paper |
Simultaneous small noise limit for singularly perturbed slow-fast coupled diffusions
Applied Mathematics and Optimization | 2021-07-15 | Paper |
A variational characterization of the optimal exit rate for controlled diffusions
Theory of Probability and Mathematical Statistics | 2021-05-27 | Paper |
On the relative value iteration with a risk-sensitive criterion
Banach Center Publications | 2021-05-20 | Paper |
Empirical Q-value iteration
Stochastic Systems | 2021-03-29 | Paper |
A variational characterization of the risk-sensitive average reward for controlled diffusions on \(\mathbb{R}^d\)
SIAM Journal on Control and Optimization | 2021-03-18 | Paper |
| Linear and dynamic programs for risk-sensitive cost minimization | 2021-03-14 | Paper |
A concentration bound for stochastic approximation via Alekseev's formula
Stochastic Systems | 2020-06-18 | Paper |
Metastability in stochastic replicator dynamics
Dynamic Games and Applications | 2019-12-18 | Paper |
Metastability in stochastic replicator dynamics
Dynamic Games and Applications | 2019-12-18 | Paper |
| Postponing collapse: ergodic control with a probabilistic constraint | 2019-11-20 | Paper |
Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents
MCSS. Mathematics of Control, Signals, and Systems | 2019-11-07 | Paper |
On the fastest finite Markov processes
Journal of Mathematical Analysis and Applications | 2019-10-04 | Paper |
LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The NonErgodic Case
SIAM Journal on Control and Optimization | 2019-08-30 | Paper |
Linear programming formulation of long-run average optimal control problem
Journal of Optimization Theory and Applications | 2019-06-07 | Paper |
Aerial monitoring of slow moving convoys using elliptical orbits
European Journal of Control | 2019-05-20 | Paper |
Opportunistic Scheduling as Restless Bandits
IEEE Transactions on Control of Network Systems | 2019-03-29 | Paper |
Distributed stochastic approximation with local projections
SIAM Journal on Optimization | 2018-12-19 | Paper |
Whittle Index Policy for Crawling Ephemeral Content
IEEE Transactions on Control of Network Systems | 2018-12-19 | Paper |
Gradient estimation with simultaneous perturbation and compressive sensing
(available as arXiv preprint) | 2018-11-22 | Paper |
| Gradient estimation with simultaneous perturbation and compressive sensing | 2018-11-22 | Paper |
| Mean field limits through local interactions | 2018-11-19 | Paper |
Reinforcement learning, sequential Monte Carlo and the EM algorithm
Sādhanā | 2018-10-31 | Paper |
| Distributed and asynchronous methods for semi-supervised learning | 2018-10-26 | Paper |
Controlled equilibrium selection in stochastically perturbed dynamics
The Annals of Probability | 2018-10-24 | Paper |
Controlled equilibrium selection in stochastically perturbed dynamics
The Annals of Probability | 2018-10-24 | Paper |
| Concentration bounds for two time scale stochastic approximation | 2018-06-28 | Paper |
Whittle Index for Partially Observed Binary Markov Decision Processes
IEEE Transactions on Automatic Control | 2018-06-27 | Paper |
Q-learning for Markov decision processes with a satisfiability criterion
Systems & Control Letters | 2018-05-16 | Paper |
| An ergodic Stackelberg team problem for controlled diffusions | 2018-05-09 | Paper |
Approachability in Stackelberg stochastic games with vector costs
Dynamic Games and Applications | 2018-04-03 | Paper |
A Distributed Boyle--Dykstra--Han Scheme
SIAM Journal on Optimization | 2017-09-07 | Paper |
Structural Properties of Optimal Transmission Policies Over a Randomly Varying Channel
IEEE Transactions on Automatic Control | 2017-08-08 | Paper |
Distributed Reinforcement Learning via Gossip
IEEE Transactions on Automatic Control | 2017-07-27 | Paper |
Actor-critic algorithms with online feature adaptation
ACM Transactions on Modeling and Computer Simulation | 2017-06-30 | Paper |
Dynamic Cesaro-Wardrop equilibration in networks
IEEE Transactions on Automatic Control | 2017-06-20 | Paper |
A correction to ``A relative value iteration algorithm for nondegenerate controlled diffusions''
SIAM Journal on Control and Optimization | 2017-06-07 | Paper |
A variational formula for risk-sensitive reward
SIAM Journal on Control and Optimization | 2017-05-24 | Paper |
Manufacturing Consent
IEEE Transactions on Automatic Control | 2017-05-16 | Paper |
Risk-Constrained Markov Decision Processes
IEEE Transactions on Automatic Control | 2017-05-16 | Paper |
Risk-sensitive control and an abstract Collatz-Wielandt formula
Journal of Theoretical Probability | 2017-01-10 | Paper |
Event-driven stochastic approximation
Indian Journal of Pure & Applied Mathematics | 2016-12-13 | Paper |
Nonlinear gossip
SIAM Journal on Control and Optimization | 2016-06-23 | Paper |
Correction to: ``Transmission rate control over randomly varying channels''
Probability in the Engineering and Informational Sciences | 2016-05-23 | Paper |
Gaussian approximations in high dimensional estimation
Systems & Control Letters | 2016-05-20 | Paper |
| scientific article; zbMATH DE number 6520436 (Why is no real title available?) | 2015-12-11 | Paper |
Relative Value Iteration for Stochastic Differential Games
Annals of the International Society of Dynamic Games | 2014-10-31 | Paper |
A stochastic Kaczmarz algorithm for network tomography
Automatica | 2014-10-20 | Paper |
Convergence of the relative value iteration for the ergodic control problem of nondegenerate diffusions under near-monotone costs
SIAM Journal on Control and Optimization | 2014-07-30 | Paper |
Asymptotics of the Invariant Measure in Mean Field Models with Jumps
(available as arXiv preprint) | 2014-07-21 | Paper |
Stochastic approximation with long range dependent and heavy tailed noise
Queueing Systems | 2013-11-25 | Paper |
Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control
Automatica | 2013-08-28 | Paper |
Markov chains, Hamiltonian cycles and volumes of convex bodies
Journal of Global Optimization | 2013-04-08 | Paper |
A relative value iteration algorithm for nondegenerate controlled diffusions
SIAM Journal on Control and Optimization | 2012-11-29 | Paper |
Hamiltonian cycle problem and Markov chains.
International Series in Operations Research & Management Science | 2012-02-14 | Paper |
| Ergodic control of diffusion processes. | 2011-12-19 | Paper |
| scientific article; zbMATH DE number 5979097 (Why is no real title available?) | 2011-11-24 | Paper |
| scientific article; zbMATH DE number 5957388 (Why is no real title available?) | 2011-10-12 | Paper |
Optimal Distributed Uplink Channel Allocation: A Constrained MDP Formulation
Annals of the International Society of Dynamic Games | 2011-08-08 | Paper |
A learning algorithm for risk-sensitive cost
Mathematics of Operations Research | 2011-04-27 | Paper |
Uniform recurrence properties of controlled diffusions and applications to optimal control
SIAM Journal on Control and Optimization | 2011-03-21 | Paper |
ERRATUM: White-Noise Representations in Stochastic Realization Theory
SIAM Journal on Control and Optimization | 2011-03-21 | Paper |
On a controlled eigenvalue problem
Systems & Control Letters | 2011-01-12 | Paper |
Application of nonlinear filtering to credit risk
Operations Research Letters | 2010-12-23 | Paper |
Singular perturbations in risk-sensitive stochastic control
SIAM Journal on Control and Optimization | 2010-12-03 | Paper |
Erratum to: Risk-sensitive control with near monotone cost
Applied Mathematics and Optimization | 2010-12-03 | Paper |
Erratum to: Risk-sensitive control with near monotone cost
Applied Mathematics and Optimization | 2010-11-22 | Paper |
Risk-sensitive control with near monotone cost
Applied Mathematics and Optimization | 2010-11-22 | Paper |
On the Hamiltonicity gap and doubly stochastic matrices
Random Structures & Algorithms | 2010-11-09 | Paper |
A new Markov selection procedure for degenerate diffusions
Journal of Theoretical Probability | 2010-10-13 | Paper |
