PNAct trains a safe RL agent to take unsafe actions only when a hidden trigger is present, while keeping normal safe behavior and reward when the trigger is absent.
Constrained policy optimiza- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
PNAct trains a safe RL agent to take unsafe actions only when a hidden trigger is present, while keeping normal safe behavior and reward when the trigger is absent.