Search Results for author: Vijay Gupta

Found 18 papers, 6 papers with code

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

1 code implementation6 Mar 2024 Wesley A. Suttle, Vipul K. Sharma, Krishna C. Kosaraju, S. Sivaranjani, Ji Liu, Vijay Gupta, Brian M. Sadler

We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory.

reinforcement-learning Reinforcement Learning (RL) +1

Towards Model-Free LQR Control over Rate-Limited Channels

no code implementations2 Jan 2024 Aritra Mitra, Lintao Ye, Vijay Gupta

Toward answering this question, we study a setting where a worker agent transmits quantized policy gradients (of the LQR cost) to a server over a noiseless channel with a finite bit-rate.


Intrinsic and extrinsic deep learning on manifolds

no code implementations16 Feb 2023 Yihao Fang, Ilsang Ohn, Vijay Gupta, Lizhen Lin

We propose extrinsic and intrinsic deep neural network architectures as general frameworks for deep learning on manifolds.

Learning Decentralized Linear Quadratic Regulator with $\sqrt{T}$ Regret

no code implementations17 Oct 2022 Lintao Ye, Ming Chi, Ruiquan Liao, Vijay Gupta

Under the assumption that the system is stable or given a known stabilizing controller, we show that our controller enjoys an expected regret that scales as $\sqrt{T}$ with the time horizon $T$ for the case of partially nested information pattern.

Cooperative Actor-Critic via TD Error Aggregation

no code implementations25 Jul 2022 Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta

In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function.

Multi-agent Reinforcement Learning Reinforcement Learning (RL)

Finite-Time Error Bounds for Distributed Linear Stochastic Approximation

no code implementations NeurIPS 2021 Yixuan Lin, Vijay Gupta, Ji Liu

While the convergence of consensus-based stochastic approximation algorithms when the interconnection among the agents is described by doubly stochastic matrices (at least in expectation) has been studied, less is known about the case when the interconnection matrix is simply stochastic.

Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation

1 code implementation12 Nov 2021 Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta

We show that in the presence of Byzantine agents, whose estimation and communication strategies are completely arbitrary, the estimates of the cooperative agents converge to a bounded consensus value with probability one, provided that there are at most $H$ Byzantine agents in the neighborhood of each cooperative agent and the network is $(2H+1)$-robust.

Multi-agent Reinforcement Learning reinforcement-learning +1

On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure

no code implementations14 Oct 2021 Lintao Ye, Hao Zhu, Vijay Gupta

We study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure, when the system model is unknown.

Data-Driven Contract Design for Multi-Agent Systems with Collusion Detection

no code implementations6 May 2021 Nayara Aguiar, Parv Venkitasubramaniam, Vijay Gupta

For a duopoly in which agents are coupled in their payments, we show that if the principal and the agents interact finitely many times, the agents can derive rent by colluding even if the principal knows the types of the agents.

EventGraD: Event-Triggered Communication in Parallel Machine Learning

2 code implementations12 Mar 2021 Soumyadip Ghosh, Bernardo Aquino, Vijay Gupta

To relieve some of this overhead, in this paper, we present EventGraD - an algorithm with event-triggered communication for stochastic gradient descent in parallel machine learning.

BIG-bench Machine Learning

Adversarial attacks in consensus-based multi-agent reinforcement learning

no code implementations11 Mar 2021 Martin Figura, Krishna Chaitanya Kosaraju, Vijay Gupta

Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature.

Multi-agent Reinforcement Learning reinforcement-learning +1

Data-Driven Incident Detection in Power Distribution Systems

no code implementations25 Feb 2021 Nayara Aguiar, Vijay Gupta, Rodrigo D. Trevizan, Babu R. Chalamala, Raymond H. Byrne

In a power distribution network with energy storage systems (ESS) and advanced controls, traditional monitoring and protection schemes are not well suited for detecting anomalies such as malfunction of controllable devices.

Data Augmentation

On Stability and Convergence of Distributed Filters

no code implementations22 Feb 2021 Sayed Pouria Talebi, Stefan Werner, Vijay Gupta, Yih-Fang Huang

The paradigm of stability and convergence in distributed filtering is revised in this manuscript.

On the Complexity of Sequential Incentive Design

1 code implementation16 Jul 2020 Yagiz Savas, Vijay Gupta, Ufuk Topcu

We model the agent's behavior as a Markov decision process, express its intrinsic motivation as a reward function, which belongs to a finite set of possible reward functions, and consider the incentives as additional rewards offered to the agent.

Optimization and Control

Data-driven Identification of Approximate Passive Linear Models for Nonlinear Systems

no code implementations L4DC 2020 S Sivaranjani, Etika Agarwal, Vijay Gupta

In model-based approaches to learning for controller design, it is important to first identify a system model from input-output data.

Encoding Multi-Resolution Brain Networks Using Unsupervised Deep Learning

no code implementations13 Aug 2017 Arash Rahnama, Abdullah Alchihabi, Vijay Gupta, Panos Antsaklis, Fatos T. Yarman Vural

We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolutions.

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