Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks.
Litian LiangYaosheng XuStephen McAleerDailin HuAlexander IhlerPieter AbbeelRoy FoxPublished in: ICML (2022)
Keyphrases
- temporal difference
- function approximation
- td learning
- evaluation function
- reinforcement learning
- monte carlo
- action selection
- reinforcement learning algorithms
- model free
- step size
- temporal difference learning
- supervised learning
- policy iteration
- neural network
- density estimation
- learning algorithm
- policy evaluation
- data sets
- training set
- importance sampling
- variance reduction