Learning generalized Nash equilibria in multi-agent dynamical systems via extremum seeking control.
Suad KrilasevicSergio GrammaticoPublished in: Autom. (2021)
Keyphrases
- dynamical systems
- multi agent
- stochastic games
- control theory
- nash equilibria
- reinforcement learning
- predictive state representations
- multiagent learning
- learning algorithm
- learning tasks
- dynamic systems
- partially observable
- single agent
- supervised learning
- control system
- dynamic environments
- differential equations
- adaptive control
- state space
- multi agent systems