On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes

Mar-14-2024, 11:54:56 GMT–Neural Information Processing Systems

We consider infinite-horizon stationary γ-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy.

algorithm, non-stationary policy, policy iteration, (10 more...)

Neural Information Processing Systems

Mar-14-2024, 11:54:56 GMT

Conferences PDF

Country:
- Europe > France (0.04)
- North America
  - United States
    - New York (0.04)
    - Florida > Broward County
      - Fort Lauderdale (0.04)
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
- Asia > Middle East
  - Israel > Haifa District > Haifa (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.71)