Decentralized approximate dynamic programming for dynamic networks of agents.
Hariharan LakshmananDaniela Pucci de FariasPublished in: ACC (2006)
Keyphrases
- dynamic networks
- approximate dynamic programming
- multi agent
- linear program
- multi agent systems
- dynamic programming
- reinforcement learning
- network structure
- multiple agents
- dynamic behavior
- network analysis
- temporal evolution
- step size
- average cost
- real world networks
- control policy
- biological networks
- action selection
- policy iteration
- machine learning