Tactics of Adversarial Attack on Deep Reinforcement Learning Agents

Yen-Chen Lin, Zhang-Wei Hong, Yuan-Hong Liao, Meng-Li Shih, Ming-Yu Liu, Min Sun

Feb 17, 2017 (modified: Apr 11, 2017) ICLR 2017 workshop submission readers: everyone
  • Abstract: We introduce two novel tactics for adversarial attack on deep reinforcement learning (RL) agents: strategically-timed and enchanting attack. For strategically- timed attack, our method selectively forces the deep RL agent to take the least likely action. For enchanting attack, our method lures the agent to a target state by staging a sequence of adversarial attacks. We show that both DQN and A3C agents are vulnerable to our proposed tactics of adversarial attack.
  • TL;DR: We propose two tactics of adversarial attacks for deep reinforcement learning and show their strength.
  • Keywords: Deep learning, Reinforcement Learning
  • Conflicts: nvidia.com, nthu.edu.tw, merl.com
0 Replies