V ariance-Aware Off-Policy Evaluation with Linear Function Approximation

Aug-14-2025, 05:18:23 GMT–Neural Information Processing Systems

We show that our algorithm achieves a tighter error bound than the best-known result.

artificial intelligence, machine learning, reinforcement learning, (11 more...)

Neural Information Processing Systems

Aug-14-2025, 05:18:23 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- North America > United States
  - California > Los Angeles County > Los Angeles (0.28)

Genre:
- Research Report (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Reinforcement Learning (1.00)
    - Representation & Reasoning > Uncertainty
      - Fuzzy Logic (0.42)
  - Data Science (1.00)