Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning.
Young WuJeremy McMahanXiaojin ZhuQiaomin XiePublished in: AAAI (2023)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- learning agent
- multi agent
- stochastic games
- learning agents
- multi agent systems
- average reward
- multi agent learning
- optimal policy
- function approximation
- solving problems
- learning capabilities
- learning process
- state space
- incomplete information
- reinforcement learning algorithms
- distributed control