Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis.
Haotian GuXin GuoXiaoli WeiRenyuan XuPublished in: SIAM J. Math. Data Sci. (2021)
Keyphrases
- complexity analysis
- multi agent reinforcement learning
- cooperative
- multi agent
- theoretical analysis
- learning agents
- multi agent systems
- reinforcement learning
- multi agent learning
- belief networks
- lower bound
- convergence rate
- stochastic approximation
- markov random field
- first order logic
- reinforcement learning algorithms
- game theory
- learning agent
- markov chain
- distributed control
- state space