no code implementations • 21 Jan 2024 • Sharu Theresa Jose, Shana Moothedath
We explore a stochastic contextual linear bandit problem where the agent observes a noisy, corrupted version of the true context through a noise channel with an unknown noise parameter.
no code implementations • 21 Jan 2024 • Jiabin Lin, Shana Moothedath
We prove the regret and communication bounds on the algorithm.
no code implementations • 8 Nov 2023 • Geethu Joseph, Shana Moothedath, Jiabin Lin
This paper studies the problem of modifying the input matrix of a structured system to make the system strongly structurally controllable.
no code implementations • 29 Mar 2023 • Jiabin Lin, Shana Moothedath
We study the problem of federated stochastic multi-arm contextual bandits with unknown contexts, in which M agents are faced with different bandits and collaborate to learn.
no code implementations • 28 Jul 2022 • Jiabin Lin, Shana Moothedath
We consider the problem where M agents collaboratively interact with an instance of a stochastic K-armed contextual bandit, where K>>M.
no code implementations • 29 Mar 2022 • Jiabin Lin, Xian Yeow Lee, Talukder Jubery, Shana Moothedath, Soumik Sarkar, Baskar Ganapathysubramanian
In this paper, we formulate a conservative stochastic contextual bandit formulation for real-time decision making when an adversary chooses a distribution on the set of possible contexts and the learner is subject to certain safety/performance constraints.
1 code implementation • 24 Jul 2020 • Shana Moothedath, Dinuka Sahabandu, Joey Allen, Linda Bushnell, Wenke Lee, Radha Poovendran
Our game model has imperfect information as the players do not have information about the actions of the opponent.
Computer Science and Game Theory Cryptography and Security