Picture for Arunselvan Ramaswamy

Arunselvan Ramaswamy

A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks

Add code
May 20, 2023
Viaarxiv icon

Stability and Convergence of Distributed Stochastic Approximations with large Unbounded Stochastic Information Delays

Add code
May 11, 2023
Viaarxiv icon

Distributed gradient-based optimization in the presence of dependent aperiodic communication

Add code
Jan 27, 2022
Viaarxiv icon

Asymptotic Convergence of Deep Multi-Agent Actor-Critic Algorithms

Add code
Jan 03, 2022
Figure 1 for Asymptotic Convergence of Deep Multi-Agent Actor-Critic Algorithms
Viaarxiv icon

Theory of Deep Q-Learning: A Dynamical Systems Perspective

Add code
Aug 25, 2020
Figure 1 for Theory of Deep Q-Learning: A Dynamical Systems Perspective
Figure 2 for Theory of Deep Q-Learning: A Dynamical Systems Perspective
Figure 3 for Theory of Deep Q-Learning: A Dynamical Systems Perspective
Figure 4 for Theory of Deep Q-Learning: A Dynamical Systems Perspective
Viaarxiv icon

Deep reinforcement learning for scheduling in large-scale networked control systems

Add code
May 15, 2019
Figure 1 for Deep reinforcement learning for scheduling in large-scale networked control systems
Figure 2 for Deep reinforcement learning for scheduling in large-scale networked control systems
Figure 3 for Deep reinforcement learning for scheduling in large-scale networked control systems
Figure 4 for Deep reinforcement learning for scheduling in large-scale networked control systems
Viaarxiv icon

DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme

Add code
Mar 17, 2019
Figure 1 for DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme
Figure 2 for DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme
Figure 3 for DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme
Figure 4 for DSPG: Decentralized Simultaneous Perturbations Gradient Descent Scheme
Viaarxiv icon

Multi-Stage Reinforcement Learning For Object Detection

Add code
Oct 26, 2018
Figure 1 for Multi-Stage Reinforcement Learning For Object Detection
Figure 2 for Multi-Stage Reinforcement Learning For Object Detection
Figure 3 for Multi-Stage Reinforcement Learning For Object Detection
Figure 4 for Multi-Stage Reinforcement Learning For Object Detection
Viaarxiv icon

Analysis of Set-Valued Stochastic Approximations: Applications to Noisy Approximate Value and Fixed point Iterations

Add code
Sep 04, 2018
Viaarxiv icon

DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling

Add code
Jun 13, 2018
Figure 1 for DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling
Figure 2 for DeepCAS: A Deep Reinforcement Learning Algorithm for Control-Aware Scheduling
Viaarxiv icon