Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium.
Yu-Guan HsiehKimon AntonakopoulosPanayotis MertikopoulosPublished in: COLT (2021)
Keyphrases
- nash equilibrium
- adaptive learning
- game theory
- profit maximizing
- nash equilibria
- worst case
- game theoretic
- regret bounds
- solution concepts
- stochastic games
- mixed strategy
- fictitious play
- repeated games
- learning objects
- stackelberg game
- variational inequalities
- pure strategy
- multi armed bandit
- incomplete information
- regret minimization
- lower bound
- pure nash equilibria
- reinforcement learning
- dynamic programming
- optimal control
- concept maps
- linear regression
- resource allocation
- upper bound
- learning environment
- machine learning
- pure nash equilibrium
- learning activities
- np hard