Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

CoRR(2023)

引用 0|浏览7
暂无评分
摘要
We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by unknown algorithms and requires limited attack budgets and computational resources. We leverage a general framework and find conditions to ensure efficient attack under a general assumption of the learning algorithms. We show that our attack is optimal in our framework under the conditions. We experimentally verify that with limited budgets, our attack efficiently leads the learning agent to various target policies under a diverse set of popular DRL environments and state-of-the-art learners.
更多
查看译文
关键词
reward,reinforcement,online deep
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络