Unified reinforcement Q-learning for mean field game and control problems.
Andrea AngiuliJean-Pierre FouqueMathieu LaurièrePublished in: Math. Control. Signals Syst. (2022)
Keyphrases
- control problems
- reinforcement learning
- markov games
- function approximation
- reinforcement learning algorithms
- state space
- optimal control
- queueing systems
- model free
- game theory
- reinforcement learning methods
- markov decision processes
- learning algorithm
- computer games
- continuous state and action spaces
- agent learns
- stochastic games
- multi agent
- optimal policy
- continuous state spaces
- game playing
- closed form
- temporal difference
- adaptive control
- belief networks
- action selection
- nash equilibria
- stochastic control
- state action
- markov random field
- least squares
- rl algorithms
- machine learning
- markov chain
- function approximators
- partially observable markov decision processes
- single agent