Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis. (arXiv:2208.00081v1 [cs.LG])

Meta reinforcement learning (meta RL), as a combination of meta-learning
ideas and reinforcement learning (RL), enables the agent to adapt to different
tasks using a few samples. However, this sampling-based adaptation also makes
meta RL vulnerable to adversarial attacks. By manipulating the reward feedback
from sampling processes in meta RL, an attacker can mislead the agent into
building wrong knowledge from training experience, which deteriorates the
agent's performance when dealing with different tasks after adaptation. This
paper provides a game-theoretical …

analysis attacks complexity lg meta