Adaptive Discounting of Training Time Attacks

no code implementations • 5 Jan 2024 • Ridhima Bector, Abhay Aradhya, Chai Quek, Zinovi Rabinovich

In this work, we show that a C-TTA is possible even when the target behaviour is un-adoptable due to both environment dynamics as well as non-optimality with respect to the victim objective(s).

Reinforcement Learning (RL)