Reinforcement Learning for Mean Field Games with Strategic Complementarities.
Ki-Yeob LeeDesik RengarajanDileep M. KalathilSrinivas ShakkottaiPublished in: AISTATS (2021)
Keyphrases
- reinforcement learning
- action sets
- learning agents
- multi agent decision making
- function approximation
- reinforcement learning agents
- markov random field
- state space
- case study
- video games
- computer games
- closed form
- game design
- machine learning
- reinforcement learning algorithms
- game theory
- temporal difference learning
- multiagent learning
- belief networks
- markov decision processes
- multi agent
- continuous time bayesian networks
- model free
- game playing
- markov networks
- nash equilibria
- decision making
- temporal difference
- bayesian inference
- dynamic programming
- learning process
- optimal control
- knowledge management
- business models
- em algorithm
- optimal policy
- game play
- loopy belief propagation
- probabilistic model
- monte carlo
- partition function
- conditional random fields
- learning agent
- fixed point
- nash equilibrium
- educational games
- posterior distribution