Output-feedback optimized consensus for directed graph multi-agent systems based on reinforcement learning and subsystem error derivatives.
Dongdong LiJiuxiang DongPublished in: Inf. Sci. (2023)
Keyphrases
- directed graph
- multi agent systems
- reinforcement learning
- multi agent reinforcement learning
- random walk
- multi agent
- error rate
- higher order
- directed acyclic graph
- shortest path problem
- learning algorithm
- state space
- function approximation
- feedback loop
- maximum flow
- cooperative
- agent technology
- strongly connected
- multi agent environments
- agent systems
- single agent
- graph structure
- reinforcement learning algorithms
- model free
- game theory
- markov decision processes
- relevance feedback
- undirected graph
- source node
- dynamic programming
- directed edges