Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning.

You Qiaoben Chengyang Ying Xinning Zhou Hang Su Jun Zhu Bo Zhang

Published in: CoRR (2021)

Keyphrases

reinforcement learning
multi agent
function approximation
neural network
genetic algorithm
countermeasures
model free
reinforcement learning algorithms
learning process
email
dynamic programming
state space
markov decision processes
temporal difference
deep learning
policy search