Amin Rakhsha
发表
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
pdf
Xiaojin Zhu,
Adish Singla,
Goran Radanovic,
2020,
ICML.
Xiaojin Zhu,
Adish Singla,
Goran Radanovic,
2020,
J. Mach. Learn. Res..
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
pdf
Xiaojin Zhu,
Xuezhou Zhang,
Adish Singla,
2021,
ArXiv.
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
pdf
Xiaojin Zhu,
Adish Singla,
Goran Radanovic,
2020,
ICML.