Online optimal consensus control of unknown linear multi-agent systems via time-based adaptive dynamic programming.
Yifan LiuTieshan LiQi-He ShanRenhai YuYue WuC. L. Philip ChenPublished in: Neurocomputing (2020)
Keyphrases
- dynamic programming
- optimal control
- multi agent systems
- online learning
- semi infinite programming
- control strategy
- piecewise linear
- state space
- linear programming
- adaptive control
- control system
- game theory
- control method
- optimal linear
- control theory
- exhaustive search
- reinforcement learning
- worst case
- coarse to fine
- greedy algorithm
- closed form
- optimal policy
- multi agent
- adaptive neural
- agent architecture
- markov decision processes
- autonomous agents
- linear systems
- online algorithms
- learning algorithm