The authors define a sequence-level coverage coefficient, claim exponential error amplification, and use rare-pattern deletion to poison offline RL datasets.
Policy teaching via environment poisoning: Training-time adversarial attacks against re- inforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning
The authors define a sequence-level coverage coefficient, claim exponential error amplification, and use rare-pattern deletion to poison offline RL datasets.