no code implementations • 20 May 2023 • Arunselvan Ramaswamy, Shalabh Bhatnagar, Naman Saxena
We show, in theory and through experiments, that our algorithm updates have low variance, and the training loss reduces in a smooth manner.
no code implementations • 11 May 2023 • Adrian Redder, Arunselvan Ramaswamy, Holger Karl
We generalize the Borkar-Meyn stability Theorem (BMT) to distributed stochastic approximations (SAs) with information delays that possess an arbitrary moment bound.
no code implementations • 27 Jan 2022 • Adrian Redder, Arunselvan Ramaswamy, Holger Karl
We show: If for any $p \ge0$ the processes that describe the success of communication between agents in a SSC network are $\alpha$-mixing with $n^{p-1}\alpha(n)$ summable, then the associated AoI processes are stochastically dominated by a random variable with finite $p$-th moment.
no code implementations • 3 Jan 2022 • Adrian Redder, Arunselvan Ramaswamy, Holger Karl
We prove the asymptotic convergence of 3DPG even in the presence of potentially unbounded Age of Information (AoI).
no code implementations • 25 Aug 2020 • Arunselvan Ramaswamy, Eyke Hüllermeier
Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function.
no code implementations • 15 May 2019 • Adrian Redder, Arunselvan Ramaswamy, Daniel E. Quevedo
This work considers the problem of control and resource scheduling in networked systems.
no code implementations • 17 Mar 2019 • Arunselvan Ramaswamy
This algorithm is a two fold improvement over the classic Simultaneous Perturbation Stochastic Approximations (SPSA) algorithm.
1 code implementation • 15 Oct 2018 • Jonas Koenig, Simon Malberg, Martin Martens, Sebastian Niehaus, Artus Krohn-Grimberghe, Arunselvan Ramaswamy
We compare an approach that is based purely on zoom actions with one that is extended by a second refinement stage to fine-tune the bounding box after each zoom step.
no code implementations • 8 Mar 2018 • Burak Demirel, Arunselvan Ramaswamy, Daniel E. Quevedo, Holger Karl
The main contribution of this paper is to develop a deep reinforcement learning-based \emph{control-aware} scheduling (\textsc{DeepCAS}) algorithm to tackle these issues.
no code implementations • 22 Feb 2018 • Arunselvan Ramaswamy, Shalabh Bhatnagar, Daniel E. Quevedo
In this paper, we present verifiable sufficient conditions for stability and convergence of asynchronous SAs with biased approximation errors.
no code implementations • 14 Sep 2017 • Arunselvan Ramaswamy, Shalabh Bhatnagar
In this paper, we consider the stochastic iterative counterpart of the value iteration scheme wherein only noisy and possibly biased approximations of the Bellman operator are available.
no code implementations • 1 Apr 2016 • Arunselvan Ramaswamy, Shalabh Bhatnagar
The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically.
no code implementations • 23 Apr 2015 • Arunselvan Ramaswamy, Shalabh Bhatnagar
Analyzing this class of algorithms is important, since many reinforcement learning (RL) algorithms can be cast as SAs driven by a `controlled Markov' process.
no code implementations • 6 Feb 2015 • Arunselvan Ramaswamy, Shalabh Bhatnagar
In this paper the stability theorem of Borkar and Meyn is extended to include the case when the mean field is a differential inclusion.
no code implementations • 6 Feb 2015 • Arunselvan Ramaswamy, Shalabh Bhatnagar
In this paper we present a framework to analyze the asymptotic behavior of two timescale stochastic approximation algorithms including those with set-valued mean fields.