Search Results for author: Vijay Subramanian

Found 7 papers, 2 papers with code

Rarest-First with Probabilistic-Mode-Suppression

no code implementations1 Nov 2022 Nouman Khan, Mehrdad Moharrami, Vijay Subramanian

In this work, we propose a tunable piece-selection policy that minimizes this (undesirable) requisite by combining the (work-conserving but not stabilizing) rarest-first protocol with only an appropriate share of the (non-work conserving and stabilizing) mode-suppression protocol.

OpenGridGym: An Open-Source AI-Friendly Toolkit for Distribution Market Simulation

1 code implementation6 Mar 2022 Rayan El Helou, Kiyeob Lee, Dongqi Wu, Le Xie, Srinivas Shakkottai, Vijay Subramanian

This paper presents OpenGridGym, an open-source Python-based package that allows for seamless integration of distribution market simulation with state-of-the-art artificial intelligence (AI) decision-making algorithms.

Decision Making

Learning a Discrete Set of Optimal Allocation Rules in Queueing Systems with Unknown Service Rates

no code implementations4 Feb 2022 Saghar Adler, Mehrdad Moharrami, Vijay Subramanian

In our problem, certainty equivalent control switches between an always admit policy (always explore) and a never admit policy (immediately terminate learning), which is distinct from the adaptive control literature.

Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure

no code implementations1 Nov 2021 Hsu Kao, Chen-Yu Wei, Vijay Subramanian

For the bandit setting, we propose a hierarchical bandit algorithm that achieves a near-optimal gap-independent regret of $\widetilde{\mathcal{O}}(\sqrt{ABT})$ and a near-optimal gap-dependent regret of $\mathcal{O}(\log(T))$, where $A$ and $B$ are the numbers of actions of the leader and the follower, respectively, and $T$ is the number of steps.

Multi-agent Reinforcement Learning Multi-Armed Bandits +2

Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning

no code implementations25 Oct 2021 Hsu Kao, Vijay Subramanian

Due to information asymmetry, finding optimal policies for Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) is hard with the complexity growing doubly exponentially in the horizon length.

Multi-agent Reinforcement Learning reinforcement-learning +1

Empirical Policy Evaluation with Supergraphs

no code implementations18 Feb 2020 Daniel Vial, Vijay Subramanian

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

On the role of clustering in Personalized PageRank estimation

1 code implementation4 Jun 2017 Daniel Vial, Vijay Subramanian

We then show that the common underlying graph can be leveraged to efficiently and jointly estimate PPR for many pairs, rather than treating each pair separately using the primitive algorithm.

Social and Information Networks

Cannot find the paper you are looking for? You can Submit a new open access paper.