Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning.
Zida WuMathieu LaurièreSamuel Jia Cong ChuaMatthieu GeistOlivier PietquinAnkur MehtaPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- online game
- action sets
- learning agents
- real time
- function approximation
- markov decision processes
- video games
- educational games
- bayesian inference
- online learning
- learning process
- machine learning
- computer games
- closed form
- field of view
- em algorithm
- dynamic programming
- posterior distribution
- model free
- action space
- genetic algorithm
- temporal difference learning