Gradient Temporal Difference with Momentum: Stability and Convergence.
Rohan DebShalabh BhatnagarPublished in: AAAI (2022)
Keyphrases
- temporal difference
- td learning
- step size
- evaluation function
- reinforcement learning
- convergence rate
- function approximation
- learning rate
- monte carlo
- gradient method
- convergence speed
- temporal difference learning
- model free
- reinforcement learning algorithms
- policy evaluation
- policy gradient
- temporal difference methods
- policy iteration
- action selection
- supervised learning
- multi objective
- e learning
- reinforcement learning problems
- machine learning
- predictive state representations
- neural network