Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates.
Litian LiangYaosheng XuStephen McAleerDailin HuAlexander IhlerPieter AbbeelRoy FoxPublished in: CoRR (2021)
Keyphrases
- temporal difference
- td learning
- evaluation function
- reinforcement learning
- function approximation
- monte carlo
- temporal difference learning
- step size
- reinforcement learning algorithms
- model free
- temporal difference methods
- policy evaluation
- action selection
- supervised learning
- actor critic
- data sets
- parametric models
- expected utility
- graph cuts
- policy iteration
- function approximators
- decision making
- neural network