Transition-Informed Reinforcement Learning for Large-Scale Stackelberg Mean-Field Games.
Pengdeng LiRunsheng YuXinrun WangBo AnPublished in: AAAI (2024)
Keyphrases
- reinforcement learning
- game theory
- nash equilibria
- leader follower
- nash equilibrium
- transition model
- learning agents
- game theoretic
- mixed strategy
- stackelberg game
- real world
- em algorithm
- state space
- small scale
- belief networks
- action sets
- function approximation
- video games
- markov random field
- optimal control
- multiagent learning
- cooperative
- markov networks
- multi agent
- function approximators
- temporal difference
- imperfect information
- bayesian inference
- free energy
- state transition
- game playing
- game design
- educational games
- computer games
- fixed point
- markov decision processes
- dynamic programming
- machine learning