A Learning Rate Analysis of Reinforcement Learning Algorithms in Finite-Horizon.
Frédérick GarciaSeydina M. NdiayePublished in: ICML (1998)
Keyphrases
- learning rate
- finite horizon
- markov decision processes
- reinforcement learning algorithms
- optimal policy
- optimal stopping
- convergence rate
- neural network
- reinforcement learning
- learning algorithm
- non stationary
- np hard
- convergence speed
- state space
- support vector
- function approximation
- decision making
- machine learning