Unified Reinforcement Q-Learning for Mean Field Game and Control Problems.
Andrea AngiuliJean-Pierre FouqueMathieu LaurièrePublished in: CoRR (2020)
Keyphrases
- control problems
- reinforcement learning
- markov games
- function approximation
- reinforcement learning algorithms
- state space
- model free
- optimal control
- queueing systems
- agent learns
- learning algorithm
- game playing
- belief networks
- closed form
- markov random field
- stochastic games
- reinforcement learning methods
- continuous state and action spaces
- machine learning
- multi agent
- dynamic programming
- markov decision processes
- nash equilibrium
- computer games
- learning problems
- game theory
- optimal policy
- continuous state spaces
- policy iteration
- state action
- temporal difference learning
- continuous state
- real time
- stochastic control
- multiagent reinforcement learning
- approximate dynamic programming
- average reward
- partially observable markov decision processes
- action selection
- adaptive control