Deep Q-Learning for Nash Equilibria: Nash-DQN.
Philippe CasgrainBrian NingSebastian JaimungalPublished in: CoRR (2019)
Keyphrases
- nash equilibria
- multiagent learning
- incomplete information
- game theory
- stochastic games
- nash equilibrium
- reinforcement learning
- cooperative
- multi agent reinforcement learning
- state space
- game theoretic
- multi agent
- pure strategy
- function approximation
- reinforcement learning algorithms
- fictitious play
- solution concepts
- model free
- learning algorithm
- optimal policy
- decision making
- genetic algorithm