Reinforcement learning for control using value function approximation
This entry provides a short introduction to a class of reinforcement learning algorithms, in particular value function approximation, applied to stochastic optimal control problems. The entry demonstrates how core ideas from dynamic programming and Bellman equations are utilized in common data-drive...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Book section |
| Language: | English |
| Published: |
Springer
2021
|