Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning.
Zida WuMathieu LaurièreSamuel Jia Cong ChuaMatthieu GeistOlivier PietquinAnkur MehtaPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- online learning
- online game
- learning agents
- reinforcement learning agents
- reinforcement learning algorithms
- field of view
- video games
- function approximation
- closed form
- multi agent
- computer games
- learning algorithm
- markov decision processes
- parameter estimation
- variational methods
- em algorithm
- stochastic games
- state space
- action sets