Abstract
The dynamic graphical game is a special class of the standard dynamic game and explicitly captures the structure of a communication graph, where the information flow between the agents is governed by the communication graph topology. A novel online adaptive learning (policy iteration) solution for the graphical game is given in terms of the solution to a set of coupled graphical game Hamiltonian and Bellman equations. The policy iteration solution is developed to learn Nash solution for the dynamic graphical game online in real-time. Policy iteration convergence proof for the dynamic graphical game is given under mild condition about the graph interconnectivity properties. Critic neural network structures are used to implement the online policy iteration solution. Only partial knowledge of the dynamics is required and the tuning is done in a distributed fashion in terms of the local information available to each agent.
| Original language | English |
|---|---|
| Title of host publication | 13th International Multi-Conference on Systems, Signals and Devices, SSD 2016 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 787-797 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781509012916 |
| DOIs | |
| State | Published - 18 May 2016 |
Publication series
| Name | 13th International Multi-Conference on Systems, Signals and Devices, SSD 2016 |
|---|
Bibliographical note
Publisher Copyright:© 2016 IEEE.
Keywords
- Cooperative control
- Dynamic games
- Game theory
- Optimal control
ASJC Scopus subject areas
- Signal Processing
- Control and Systems Engineering
- Energy Engineering and Power Technology
- Control and Optimization
- Computer Networks and Communications
- Instrumentation