|
Publications
2021
- Learning in Markov decision processes under constraints
Rahul Singh, Abhishek Gupta, and Ness B Shroff
arXiv preprint arXiv:2002.12435
- Weak Continuity of Dissimilarity Metrics between Measures over Polish Spaces
Shiping Shao, Jianzong Pi, and Abhishek Gupta
in preparation
- Premptive Scheduling of EV Charging with Rate Constraints using Approximate Dynamic Programming
Abhishek Gupta Shiping Shao
in preparation
- Discrete-Time Finite-Horizon Optimization of Singularly Perturbed Control Systems
Abhishek Gupta Jianzong Pi
in preparation
- Menu Auction: A Stackelberg Game Approach
Abhishek Gupta Anuj S. Vora
in preparation
- A Dynamic Watermarking Algorithm for Finite Markov Decision Problems
Abhishek Gupta Jiacheng Tang
submitted to IEEE Transactions on Automatic Control
- Probabilistic Contraction Analysis of Iterated Random Operators
Abhishek Gupta, Rahul Jain, and Peter Glynn
submitted to IEEE Transactions on Automatic Control
- Nash Equilibrium Control Policy against Bus-off Attacks in CAN Networks
Abhishek Gupta Jiacheng Tang
submitted to IEEE Transactions on Automatic Control
- Incentive Design and Profit Sharing in Multi-modal Transportation Network
Yuntian Deng, Shiping Shao, Archak Mittal, Richard Twumasi-Boakye, James Fishelson, Abhishek Gupta, and Ness B Shroff
submitted to Transportation Research Part B: Methodological
- An Algorithm to Warm Start Perturbed (WASP) Constrained Dynamic Programs
Marcello Canova Abhishek Gupta
submitted to IEEE Open Journal of Control Systems
- Rank reduction in bimatrix games
Joseph L. Heyman and Abhishek Gupta
submitted to International Game Theory Review
- Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles
Zhaoxuan Zhu, Nicola Pivaro, Shobhit Gupta, Abhishek Gupta, and Marcello Canova
submitted to IEEE Transactions on Intelligent Vehicles, available on arXiv preprint arXiv:2105.11640
- A Deep Reinforcement Learning Framework for Eco-driving in Connected and Automated Hybrid Electric Vehicles
Zhaoxuan Zhu, Shobhit Gupta, Abhishek Gupta, and Marcello Canova
sumitted to IEEE Transactions on Intelligent Transportation Systems, available on arXiv preprint arXiv:2101.05372
- Fleet Sizing and Charger Allocation in Electric Vehicle Sharing Systems
Yuntian Deng, Abhishek Gupta, and Ness B. Shroff
Submitted to IFAC Journal of Systems and Control
- Finite Sample Analysis of Offline Reinforcement Learning with State-Dependent Action Sets
Jayanth Regatti and Abhishek Gupta
submitted to L4DC
- Change Detection of Markov Kernels using Maximum Mean Discrepancy
Hao Chen, Jiacheng Tang, and Abhishek Gupta
submitted to L4DC
- Weighted Gaussian Process Bandits for Non-stationary Environments
Yuntian Deng, Xingyu Zhou, Baekjin Kim, Ambuj Tewari, Abhishek Gupta, and Ness Shroff
submitted to 25th International Conference on Artificial Intelligence and Statistics
- *ByGARS: Byzantine SGD
with Arbitrary Number of Attackers}
Jayanth Regatti, Hao Chen, and Abhishek Gupta*
submitted to ACC 2022, arXiv preprint arXiv:2006.13421
- Offline RL With Resource Constrained Online Deployment
Jayanth Regatti, Aniket Anand Deshmukh, Frank Cheng, Young Hun Jung, Abhishek Gupta, and Urun Dogan
Submitted to ICLR 2022, arXiv preprint arXiv:2110.03165
- A Discussion of Artificial Intelligence Applications in SiC MOSFET Device Operation
Jayanth Regatti, Haoyang You, Han Wang, Jon Hall, Alec Schnabel, Boxue Hu, Julia Zhang, Jin Wang, and Abhishek Gupta
2021 IEEE International Electric Machines & Drives Conference (IEMDC)
- Two Algorithms for Computing Exact and Approximate Nash Equilibria in Bimatrix Games
Jianzong Pi, Joseph L. Heyman, and Abhishek Gupta
International Conference on Decision and Game Theory for Security
2019
- An empirical relative value learning algorithm for non-parametric mdps with continuous state space
Hiteshi Sharma, Rahul Jain, and Abhishek Gupta
2019 18th European Control Conference (ECC)
- Distributed SGD Generalizes Well Under Asynchrony
Jayanth Regatti, Gaurav Tendolkar, Yi Zhou, Abhishek Gupta, and Yingbin Liang
2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
- Traffic-Aware Adaptive Routing for Minimizing Fuel Consumption
Jayanth Regatti and Abhishek Gupta
2019 American Control Conference (ACC)
- A fast algorithm to reduce 2xn bimatrix games to rank-1 games
Joseph L. Heyman and Abhishek Gupta
2019 18th European Control Conference (ECC)
2018
- Colonel Blotto Game with Coalition Formation for Sharing Resources
Joseph L. Heyman and Abhishek Gupta
International Conference on Decision and Game Theory for Security
- Dynamic Economic Dispatch and Price Evolution under Ramping Constraints and Uncertain Demand
Abhishek Gupta, Balsam Dakhil, and Rahul Jain
2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
- Communication Link Elimination in Static LQG Teams
Jiacheng Tang and Abhishek Gupta
2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
- Selling Renewable Generation with a Penalty for Shortfall
B. Dakhil and A. {Gupta
2018 IEEE Conference on Decision and Control (CDC)
2017
- Information structures and values in zero-sum stochastic games
Ashutosh Nayyar and Abhishek Gupta
2017 American Control Conference (ACC)
2016
- Privacy-aware stochastic control with a ‘‘snoopy’’ adversary: A game-theoretic approach
Abhishek Gupta
2016 Annual Conference on Information Science and Systems (CISS)
2015
- Equilibria in two-stage electricity markets
Abhishek Gupta, Rahul Jain, Kameshwar Poolla, and Pravin Varaiya
54th IEEE Conference on Decision and Control (CDC)
- An empirical algorithm for relative value iteration for average-cost MDPs
Abhishek Gupta, Rahul Jain, and Peter W Glynn
54th IEEE Conference on Decision and Control (CDC)
- Scheduling, pricing, and efficiency of non-preemptive flexible loads under direct load control
Abhishek Gupta, Rahul Jain, and Ram Rajagopal
53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)
2014
- Dynamic incentive design in multi-stage linear-Gaussian games with asymmetric information: A common information based approach
Abhishek Gupta and Tamer Başar
53rd IEEE Conference on Decision and Control (CDC)
- A three-Stage Colonel Blotto game: When to provide more information to an adversary
Abhishek Gupta, Tamer Başar, and Galina Schwartz
Decision and Game Theory for Security, Lecture Notes in Computer Science edited by R. Poovendran and W. Saad
- A three-Stage Colonel Blotto game with applications to cyberphysical security
Abhishek Gupta, Galina Schwartz, Cédric Langbort, Shankar S. Sastry, and Tamer Başar
Proc. 2014 American Control Conference (ACC)
- On the existence of optimal strategies in multi-agent stochastic teams
Abhishek Gupta, Serdar Yüksel, Cédric Langbort, and Tamer Başar
Proc. 2014 American Control Conference (ACC)
- On the existence of optimal strategies in a class of dynamic stochastic teams
Abhishek Gupta, Serdar Yüksel, and Tamer Başar
Proc. of 53rd IEEE Conference in Decision and Control (CDC)
- Dynamic incentive design in multi-stage linear-Gaussian games of asymmetric information: A common information based approach
Abhishek Gupta and Tamer Başar
Proc. of 53rd IEEE Conference in Decision and Control (CDC)
2012
- A dynamic transmitter-jammer game with asymmetric information
Abhishek Gupta, Ashutosh Nayyar, Cédric Langbort, and Tamer Başar
Proc. 51st IEEE Conference on Decision and Control
- On myopic strategies in dynamic adversarial team decision problems
Abhishek Gupta, Pulkit Grover, Cédric Langbort, and Tamer Başar
46th Annual Conference on Information Sciences and Systems (CISS)
2011
- Decentralized Opportunistic Navigation Strategies for Multi-agent Systems in the Presence of an Adversary
Sourabh Bhattacharya, Abhishek Gupta, and Tamer Başar
Proc. IFAC World Congress
- Decentralized control of multi-agent systems with an adversarial switching topology
Abhishek Gupta, Sourabh Bhattacharya, and Tamer Başar
Infotech @ Aerospace 2011
- One-stage control over an adversarial channel with finite codelength
Abhishek Gupta, Cédric Langbort, and Tamer Başar
Proc. 50th IEEE Conference on Decision and Control
2010
- Optimal control in the presence of an intelligent jammer with limited actions
Abhishek Gupta, Cédric Langbort, and Tamer Başar
Proc. 49th IEEE Conference on Decision and Control
2021
- Multi-Objective Vehicle Rebalancing for Ridehailing System using a Reinforcement Learning Approach
Yuntian Deng, Hao Chen, Shiping Shao, Jiacheng Tang, Jianzong Pi, and Abhishek Gupta
Accepted in Journal of Management Science and Engineering
- Fitted Value Iteration in Continuous MDPs With State Dependent Action Sets
Hao Li, Shiping Shao, and Abhishek Gupta
IEEE Control Systems Letters
- Sketching for Elimination of Communication Links in LQG Teams
Jiacheng Tang and Abhishek Gupta
IEEE Control Systems Letters
- Fair Pricing of Ridehailing Services with Asymmetric Demand and Travel Time
Shiping Shao, Archak Mittal, Richard Twumasi-Boakye, and Abhishek Gupta
Accepted in IEEE Transactions on Control of Networked Systems
- Convergence of recursive stochastic algorithms using Wasserstein divergence
Abhishek Gupta and William B Haskell
SIAM Journal on Mathematics of Data Science
- Existence of Team-Optimal Strategies in Teams with Countable Observation Spaces
Abhishek Gupta
IEEE Transactions on Automatic Control
2020
- Existence of Team-Optimal Solutions in Static Teams with Common Information: A Topology of Information Approach
Abhishek Gupta
SIAM Journal on Control and Optimization
- Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms
Abhishek Gupta, Hao Chen, Jianzong Pi, and Gaurav Tendolkar
SIAM Journal on Mathematics of Data Science
2019
- Auctioning electricity under deep renewable integration using a penalty for shortfall
Balsam Dakhil and Abhishek Gupta
Sustainable Energy, Grids and Networks
2017
- Dynamic Games With Asymmetric Information and Resource Constrained Players With Applications to Security of Cyberphysical Systems
Abhishek Gupta, Cédric Langbort, and Tamer Başar
IEEE Transactions on Control of Network Systems
2014
- Common information based Markov perfect equilibria for linear-Gaussian games with asymmetric information
Abhishek Gupta, Ashutosh Nayyar, Cédric Langbort, and Tamer Başar
SIAM Journal on Control and Optimization
2015
- On the existence of optimal policies for a class of static and sequential dynamic teams
Abhishek Gupta, Serdar Yüksel, Tamer Başar, and Cédric Langbort
SIAM Journal on Control and Optimization
2014
- The topology of information on the space of probability measures over Polish spaces
Martin Barbie and Abhishek Gupta
Journal of Mathematical Economics
- Common Information Based Markov Perfect Equilibria for Stochastic Games With Asymmetric Information: Finite Games
A. Nayyar, Abhishek Gupta, C. Langbort, and T. Başar
IEEE Transactions on Automatic Control
- A Three-Stage Colonel Blotto Game with Applications to Cyber-Physical Security
Abhishek Gupta, Galina Schwartz, Cedric Langbort, S Shankar Sastry, and Tamer Başar
Technical Report No. UCBEECS-2014-19, EECS Department, University of California at Berkeley/
2013
- Jamming in mobile networks: A game-theoretic approach
Sourabh Bhattacharya, Abhishek Gupta, and Tamer Başar
Numerical Algebra, Control & Optimization
2008
- PeV scale Left–Right symmetry and Baryon asymmetry of the Universe
Anjishnu Sarkar, Abhishek, and Urjit A Yajnik
Nuclear physics B
Thesis
- Control in the presence of an intelligent jammer with limited actions
Abhishek Gupta
University of Illinois at Urbana-Champaign
Illinois, USA
- Dynamic Sequential Decision Problems with Asymmetric Information: Some Existence Results
Abhishek Gupta
University of Illinois at Urbana-Champaign
Illinois, USA
|