Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks.
Mohammad MohammadiJonathan NötherDebmalya MandalAdish SinglaGoran RadanovicPublished in: AAMAS (2023)
Keyphrases
- reinforcement learning
- multi agent
- countermeasures
- markov decision process
- optimal policy
- reward function
- multiagent systems
- security mechanisms
- function approximation
- supervised learning
- intelligent agents
- training set
- multi agent systems
- cooperative
- machine learning
- multiagent reinforcement learning
- policy search
- partially observable markov decision processes
- single agent
- watermarking algorithm
- software agents
- markov decision processes
- state space
- dynamic programming
- social networks