Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations

Cited by: 0|Bibtex|Views56|Links

Abstract:

Deep Reinforcement Learning (DRL) is vulnerable to small adversarial perturbations on state observations. These perturbations do not alter the environment directly but can mislead the agent into making suboptimal decisions. We analyze the Markov Decision Process (MDP) under this threat model and utilize tools from the neural net-work ve...More

Code:

Data:

Your rating :
0

 

Tags
Comments