Search Results for author:
Found 13 papers, 0 papers with code
Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process.
SALSA PICANTE: a machine learning attack on LWE with binary secrets
However, this attack assumes access to millions of eavesdropped LWE samples and fails at higher Hamming weights or dimensions.
Top $K$ Ranking for Multi-Armed Bandit with Noisy Evaluations
We consider a multi-armed bandit setting where, at the beginning of each round, the learner receives noisy independent, and possibly biased, \emph{evaluations} of the true reward of each arm and it selects $K$ arms with the objective of accumulating as much reward as possible over $T$ rounds.
Privacy Amplification via Shuffling for Linear Contextual Bandits
Contextual bandit algorithms are widely used in domains where it is desirable to provide a personalized service by leveraging contextual information, that may contain sensitive information that needs to be protected.
Differentially Private Exploration in Reinforcement Learning with Linear Representation
We first consider the setting of linear-mixture MDPs (Ayoub et al., 2020) (a. k. a.\ model-based setting) and provide an unified framework for analyzing joint and local differential private (DP) exploration.
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning
We also obtain a new upper bound for conservative low-rank MDP.
Encrypted Linear Contextual Bandit
A critical aspect of bandit methods is that they require to observe the contexts --i. e., individual or group-level data-- and rewards in order to solve the sequential problem.
Local Differential Privacy for Regret Minimization in Reinforcement Learning
Motivated by this, we study privacy in the context of finite-horizon Markov Decision Processes (MDPs) by requiring information to be obfuscated on the user side.
Adversarial Attacks on Linear Contextual Bandits
In many of these domains, malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior.
Improved Algorithms for Conservative Exploration in Bandits
In this case, it is desirable to deploy online learning algorithms (e. g., a multi-armed bandit algorithm) that interact with the system to learn a better/optimal policy under the constraint that during the learning process the performance is almost never worse than the performance of the baseline itself.
Conservative Exploration in Reinforcement Learning
While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward.
No-Regret Exploration in Goal-Oriented Reinforcement Learning
Many popular reinforcement learning problems (e. g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (SSP) formulation, where an agent has to achieve a goal state while minimizing the cumulative cost.
Bandits with Side Observations: Bounded vs. Logarithmic Regret
We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\epsilon$, an extra observation is gathered by the agent for free.
