Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning.
Yinglun XuQi ZengGagandeep SinghPublished in: CoRR (2022)
Keyphrases
- website
- reinforcement learning
- reinforcement learning algorithms
- state space
- balancing exploration and exploitation
- machine learning
- online learning
- function approximation
- neural network
- learning algorithm
- learning process
- real time
- markov decision processes
- security issues
- model free
- temporal difference
- data mining