On the Curses of Future and History in Future-dependent Value Functions for OPE

Feb-18-2026, 10:43:15 GMT–Neural Information Processing Systems

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon.

artificial intelligence, machine learning, reinforcement learning, (16 more...)

Neural Information Processing Systems

Feb-18-2026, 10:43:15 GMT

Conferences PDF

Country:
- North America > United States
  - Illinois > Champaign County
    - Urbana (0.04)
  - Indiana > Tippecanoe County
    - Lafayette (0.04)

Genre:
- Research Report > Experimental Study (0.92)
- Workflow (0.68)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models > Undirected Networks
      - Markov Models (1.00)
    - Reinforcement Learning (0.68)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
On the Curses of Future and History in Future-dependent Value Functions for OPE

Similar Docs Excel Report more

Title	Similarity	Source
None found