Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

Marek Petrik, Reazul Hasan Russel

Aug-20-2025, 00:18:46 GMT–Neural Information Processing Systems

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning.

ambiguity, machine learning, reinforcement learning, (12 more...)

Neural Information Processing Systems

Aug-20-2025, 00:18:46 GMT

Conferences PDF

Country:
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America
  - Canada (0.04)
  - United States > New Hampshire (0.04)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Learning Graphical Models > Directed Networks
        Bayesian Learning (0.69)
      - Reinforcement Learning (0.70)
    - Representation & Reasoning > Uncertainty
      - Bayesian Inference (0.47)
  - Data Science (0.97)

Duplicate Docs Excel Report

Title
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

Similar Docs Excel Report more

Title	Similarity	Source
None found