Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators
–Neural Information Processing Systems
It is known that policy evaluation has the interpretation of solving a generalized Bellman equation. In this paper, we derive finite-sample bounds for any general off-policy TD-like stochastic approximation algorithm that solves for the fixed-point of this generalized Bellman operator.
Neural Information Processing Systems
Aug-16-2025, 23:40:01 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Canada > Alberta (0.14)
- United States > Texas
- Travis County > Austin (0.04)
- Asia > Middle East
- Genre:
- Research Report > New Finding (0.46)
- Technology: