Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium.
Yu-Guan HsiehKimon AntonakopoulosPanayotis MertikopoulosPublished in: CoRR (2021)
Keyphrases
- nash equilibrium
- adaptive learning
- game theory
- profit maximizing
- nash equilibria
- worst case
- game theoretic
- regret bounds
- solution concepts
- stackelberg game
- fictitious play
- pure strategy
- regret minimization
- mixed strategy
- stochastic games
- learning objects
- equilibrium strategies
- cooperative
- concept maps
- convergence rate
- multi armed bandit
- pure nash equilibrium
- repeated games
- online learning
- optimal solution
- pure nash equilibria
- variational inequalities
- student model
- optimal control
- linear regression
- closed form
- resource allocation
- upper bound