Unified continuous-time q-learning for mean-field game and mean-field control problems.
Xiaoli WeiXiang YuFengyi YuanPublished in: CoRR (2024)
Keyphrases
- control problems
- reinforcement learning
- optimal control
- continuous time bayesian networks
- markov games
- markov random field
- belief networks
- markov processes
- state space
- reinforcement learning methods
- continuous state spaces
- queueing systems
- dynamic programming
- variational approximation
- adaptive control
- reinforcement learning algorithms
- closed form
- game theory
- multi agent
- control law
- finite state
- control strategy
- markov decision processes
- learning algorithm
- cooperative
- temporal difference learning
- dynamic environments
- machine learning
- action selection
- game playing
- policy iteration
- function approximation
- markov chain