Off-policy reinforcement learning for distributed output synchronization of linear multi-agent systems.
Bahare KiumarsiFrank L. LewisPublished in: SSCI (2017)
Keyphrases
- multi agent systems
- reinforcement learning
- multi agent
- cooperative multi agent systems
- multi agent reinforcement learning
- agent technology
- distributed systems
- cooperative
- distributed problem solving
- distributed environment
- multi agent environments
- learning algorithm
- distributed search
- distributed artificial intelligence
- machine learning
- spatial filters
- computing environments
- computer networks
- autonomous agents
- intelligent agents
- function approximation
- fully distributed
- game theory
- multiagent environments
- neural network
- coalition formation
- linear systems
- reinforcement learning algorithms
- agent interactions
- computational logic
- concurrent processes
- peer to peer