Stochastic Learning Rate Optimization in the Stochastic Approximation and Online Learning Settings.
Theodoros MamalisDusan M. StipanovicPetros G. VoulgarisPublished in: CoRR (2021)
Keyphrases
- stochastic approximation
- learning rate
- online learning
- monte carlo
- convergence rate
- learning algorithm
- global optimization
- adaptive learning rate
- optimization algorithm
- reinforcement learning
- convergence speed
- policy iteration
- global convergence
- rapid convergence
- active learning
- e learning
- temporal difference learning
- neural network