Deep Reinforcement Learning using Cyclical Learning Rates.
Ralf GuldeMarc TuscherAkos CsiszarOliver RiedelAlexander VerlPublished in: AI4I (2020)
Keyphrases
- learning rate
- reinforcement learning
- learning algorithm
- convergence rate
- covering numbers
- gaussian kernels
- convergence speed
- function approximation
- weight vector
- uniform convergence
- learning problems
- optimal policy
- machine learning algorithms
- supervised learning
- convergence theorem
- delta bar delta
- real valued
- generalization ability
- learning process