Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks.
Mohammad MohammadiJonathan NötherDebmalya MandalAdish SinglaGoran RadanovicPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- multi agent
- countermeasures
- optimal policy
- watermarking scheme
- reward function
- multi agent systems
- markov decision process
- state space
- security mechanisms
- action selection
- digital images
- reinforcement learning agents
- control policy
- function approximation
- software agents
- multiagent systems
- mobile agents