An online attacker knowing only which states are reachable can poison rewards and transitions to make a Q-learning agent follow a target policy in a maze.
Badrl: Sparse targeted backdoor attack against reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
An online attacker knowing only which states are reachable can poison rewards and transitions to make a Q-learning agent follow a target policy in a maze.