A novel policy iteration algorithm for solving the optimal consensus control problem of a discrete-time multiagent system with unknown dynamics.
Wenkai XuLi WangShiwen SunChengyi XiaZengqiang ChenPublished in: Sci. China Inf. Sci. (2023)
Keyphrases
- multiagent systems
- policy iteration algorithm
- finite state
- markov decision processes
- multi agent
- markov chain
- optimal control
- reinforcement learning
- multiagent planning
- multiagent architecture
- model checking
- autonomous agents
- control system
- autonomous vehicles
- multi agent systems
- policy iteration
- optimal policy
- dynamic programming
- dead zone
- robotic soccer
- action space
- control problems
- average cost
- dynamical systems
- monte carlo