Equilibrium Bandits: Learning Optimal Equilibria of Unknown Dynamics.
Siddharth ChandakIlai BistritzNicholas BambosPublished in: AAMAS (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- optimal control
- games with incomplete information
- learning process
- nash equilibrium
- knowledge acquisition
- game theory
- dynamical systems
- mobile learning
- learning systems
- inductive inference
- dynamic model
- higher education
- neural network
- dynamic programming
- np hard
- lower bound
- cooperative
- machine learning