Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning.
Ronghui MuWenjie RuanLeandro Soriano MarcolinoGaojie JinQiang NiPublished in: CoRR (2022)
Keyphrases
- multi agent reinforcement learning
- cooperative
- multi agent
- multi agent systems
- reinforcement learning
- multi agent learning
- learning agents
- optimal policy
- stochastic games
- machine learning
- neural network
- distributed control
- reward function
- evolutionary game theory
- game theory
- multiagent systems
- state space
- artificial intelligence