Aditya Mahajan

Mila > À propos de Mila > Équipe > Aditya Mahajan
Membre Académique Associé
Aditya Mahajan
Professeur agrégé, McGill University
Aditya Mahajan

Aditya Mahajan est professeur agrégé en génie électrique et informatique à l’Université McGill et membre associé de Mila. Il a obtenu un baccalauréat en génie électrique de l’Indian Institute of Technology, Kanpur, Inde, en 2003, ainsi qu’une maîtrise et un doctorat en génie électrique et en informatique de la University of Michigan, Ann Arbor, MI, États-Unis, en 2006 et 2008. De 2008 à 2010, il a été chercheur postdoctoral au département de génie électrique de la Yale University, New Haven, CT, États-Unis. 

Ses recherches portent sur le contrôle stochastique décentralisé, la théorie des équipes, la communication en temps réel, les bandits à bras multiples, les réseaux de capteurs, la théorie de l’information et les systèmes à événements discrets.

Publications

2021-11

Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach.
Abhinav Dahiya, Nima Akbarzadeh, Aditya Mahajan and Stephen L. Smith
arXiv preprint arXiv:2111.06437
(2021-11-11)
export.arxiv.orgPDF

2021-10

Robustness and sample complexity of model-based MARL for general-sum Markov games.
Jayakumar Subramanian, Amit Sinha and Aditya Mahajan
arXiv preprint arXiv:2110.02355
(2021-10-05)
128.84.4.34PDF

2021-08

A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
arXiv e-prints
(2021-08-19)
ui.adsabs.harvard.eduPDF
Scalable regret for learning to control network-coupled subsystems with unknown dynamics.
Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
arXiv e-prints
(2021-08-18)
ui.adsabs.harvard.eduPDF
Multi-Agent Estimation and Filtering for Minimizing Team Mean-Squared Error
Mohammad Afshari and Aditya Mahajan
IEEE Transactions on Signal Processing
(2021-08-16)
doi.orgPDF

2021-06

Structure-aware reinforcement learning for node-overload protection in mobile edge computing
Anirudha Jitani, Aditya Mahajan, Zhongwen Zhu, Hatem Abou-Zeid, Emmanuel Thepie Fapi and Hakimeh Purmehdi

2021-04

Maintenance of a collection of machines under partial observability: Indexability and computation of Whittle index.
Nima Akbarzadeh and Aditya Mahajan

2021-01

Multi-Agent Estimation and Filtering for Minimizing Team Mean-Squared Error
Mohammad Afshari and Aditya Mahajan
IEEE Transactions on Signal Processing
(2021-01-01)
dblp.uni-trier.de
Optimal control of network-coupled subsystems: Spectral decomposition and low-dimensional solutions
Shuang Gao and Aditya Mahajan
IEEE Transactions on Control of Network Systems
(2021-01-01)
xplorestaging.ieee.org[Also on arXiv e-prints (2020-09-25)]

2020-12

Team Optimal Control of Coupled Major-Minor Subsystems with Mean-Field Sharing
Jalal Arabneydi and Aditya Mahajan
arXiv preprint arXiv:2012.02401
(2020-12-04)
arxiv.orgPDF
Reinforcement Learning in Decentralized Stochastic Control Systems with Partial History Sharing.
Jalal Arabneydi and Aditya Mahajan
arXiv: Optimization and Control
(2020-12-02)
ui.adsabs.harvard.eduPDF
Team-Optimal Solution of Finite Number of Mean-Field Coupled LQG Subsystems.
Jalal Arabneydi and Aditya Mahajan
arXiv preprint arXiv:2012.02052
(2020-12-02)
ui.adsabs.harvard.eduPDF
Team Optimal Control of Coupled Subsystems with Mean-Field Sharing
Jalal Arabneydi and Aditya Mahajan
arXiv preprint arXiv:2012.01418
(2020-12-02)
ui.adsabs.harvard.eduPDF

2020-11

Thompson sampling for linear quadratic mean-field teams.
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar and Yi Ouyang
arXiv e-prints
(2020-11-09)
ui.adsabs.harvard.eduPDF

2020-10

Approximate information state for approximate planning and reinforcement learning in partially observed systems.
Jayakumar Subramanian, Amit Sinha, Raihan Seraj and Aditya Mahajan
arXiv preprint arXiv:2010.08843
(2020-10-17)
ui.adsabs.harvard.eduPDF

2020-09

Networked control of coupled subsystems: Spectral decomposition and low-dimensional solutions
Shuang Gao and Aditya Mahajan
(venue unknown)
(2020-09-25)

2020-08

Conditions for indexability of restless bandits and an algorithm to compute Whittle index
Nima Akbarzadeh and Aditya Mahajan
arXiv e-prints
(2020-08-13)
ui.adsabs.harvard.eduPDF
Optimal Local and Remote Controllers With Unreliable Uplink Channels: An Elementary Proof
Mohammad Afshari and Aditya Mahajan
IEEE Transactions on Automatic Control
(2020-08-01)
ieeexplore.ieee.orgPDF
Renewal Monte Carlo: Renewal Theory-Based Reinforcement Learning
Jayakumar Subramanian and Aditya Mahajan
IEEE Transactions on Automatic Control
(2020-08-01)
ieeexplore.ieee.org

2020-07

Counterexamples on the Monotonicity of Delay Optimal Strategies for Energy Harvesting Transmitters
Borna Sayedana and Aditya Mahajan
IEEE Wireless Communications Letters
(2020-07-01)
jglobal.jst.go.jpPDF

2020-06

Cross-layer communication over fading channels with adaptive decision feedback
Borna Sayedana, Aditya Mahajan and Edmund Yeh
WIOPT 2020
(2020-06-15)
ieeexplore.ieee.orgPDF
Restless bandits: Indexability and computation of Whittle index
Nima Akbarzadeh and Aditya Mahajan
Les Cahiers du GERAD
(2020-06-01)
www.gerad.ca[LATEST on None (2020-08-13)]

2020-05

Remote Estimation Over a Packet-Drop Channel With Markovian State
Jhelum Chakravorty and Aditya Mahajan
IEEE Transactions on Automatic Control
(2020-05-01)
ieeexplore.ieee.orgPDF

2020-04

Decentralized linear quadratic systems with major and minor agents and non-Gaussian noise
Mohammad Afshari and Aditya Mahajan
arxiv:eess.SY
(2020-04-24)
ui.adsabs.harvard.eduPDF

2020-02

Team Optimal Decentralized State Estimation of Linear Stochastic Processes by Agents with Non-Classical Information Structures.
Mohammad Afshari and Aditya Mahajan
arXiv: Systems and Control
(2020-02-11)
arxiv.orgPDF

Publications collected and formatted using Paperoni

array(1) { ["wp-wpml_current_language"]=> string(2) "fr" }