Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer.
Toru ShirakawaYi LiYulun WuSky QiuYuxuan LiMingduo ZhaoHiroyasu IsoMark J. van der LaanPublished in: CoRR (2024)
Keyphrases
- temporal difference
- td learning
- function approximation
- evaluation function
- reinforcement learning
- monte carlo
- reinforcement learning algorithms
- action selection
- step size
- temporal difference learning
- model free
- policy evaluation
- temporal difference methods
- fuzzy logic
- supervised learning
- neural network
- radial basis function
- policy iteration
- data sets
- least squares
- e learning