Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games.
Tianyi LinZhengyuan ZhouPanayotis MertikopoulosMichael I. JordanPublished in: ICML (2020)
Keyphrases
- multi agent learning
- game theory
- multiagent learning
- agents and multi agent systems
- game theoretic
- nash equilibrium
- learning agents
- replicator dynamics
- nash equilibria
- cooperative
- multi agent systems
- multi agent
- resource allocation
- convergence rate
- artificial intelligence
- regret minimization
- game playing
- neural network
- video games
- computer games
- stochastic games
- reinforcement learning
- evolutionary game theory
- active learning