conftrace_

reward manipulation

7 papers

Explore in graph

Co-occurring keywords

adversarial attack (1621) stochastic bandit (98) poisoning attack (98) multi-armed bandit (1098) ucb algorithm (44) reinforcement learning (4352) environment poisoning (2) policy teaching (3) security threat (5) incentive alignment (5)

Papers

Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses AISTATS 2024
Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning IJCAI 2022
Path-Specific Objectives for Safer Agent Incentives AAAI 2022
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks JMLR 2021
Adversarial Attacks on Linear Contextual Bandits NIPS 2020
Data Poisoning Attacks on Stochastic Bandits ICML 2019
Adversarial Attacks on Stochastic Bandits NIPS 2018