Search Results for author:
Found 9 papers, 0 papers with code
Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
Multi-objective optimization (MOO) aims to optimize multiple, possibly conflicting objectives with widespread applications.
Selective Uncertainty Propagation in Offline RL
We consider the finite-horizon offline reinforcement learning (RL) setting, and are motivated by the challenge of learning the policy at any step h in dynamic programming (DP) algorithms.
Multi-Player Bandits Robust to Adversarial Collisions
We provide the first decentralized and robust algorithm RESYNC for defenders whose performance deteriorates gracefully as $\tilde{O}(C)$ as the number of collisions $C$ from the attackers increases.
Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i. e., the manipulation of \emph{reward} and \emph{action}.
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification
In particular, for the case of unlimited verifications, we show that with $O(\log T)$ expected number of verifications, a simple modified version of the ETC type bandit algorithm can restore the order optimal $O(\log T)$ regret irrespective of the amount of contamination used by the attacker.
Sequential Choice Bandits with Feedback for Personalizing users' experience
We then propose bandit algorithms for the two feedback models and show that upper and lower bounds on the regret are of the order of $\tilde{O}(N^{2/3})$ and $\tilde\Omega(N^{2/3})$, respectively, where $N$ is the total number of users.
Learning-based attacks in Cyber-Physical Systems: Exploration, Detection, and Control Cost trade-offs
We study the trade-offs between the information acquired by the attacker from observations, the detection capabilities of the controller, and the control cost.
Online learning with feedback graphs and switching costs
For the two special cases of symmetric PI setting and MAB, the expected regret of both of these algorithms is order optimal in the duration of the learning process.
Distributed Chernoff Test: Optimal decision systems over networks
In the first case, the network nodes interact with each other through a central entity, which plays the role of a fusion center.
