Q-Learning With Uniformly Bounded Variance.
Adithya M. DevrajSean P. MeynPublished in: IEEE Trans. Autom. Control. (2022)
Keyphrases
- reinforcement learning
- cooperative
- learning algorithm
- model free
- state space
- multi agent
- function approximation
- stochastic approximation
- minimum variance
- optimal policy
- standard deviation
- low variance
- multi agent reinforcement learning
- action selection
- asymptotically optimal
- reward function
- maximum variance
- potential field
- temporal difference learning
- reinforcement learning algorithms
- artificial neural networks
- covariance matrix
- sufficient conditions
- least squares