Sample-EfficientReinforcementLearningIsFeasible forLinearlyRealizableMDPswithLimitedRevisiting

Feb-9-2026, 18:43:37 GMT–Neural Information Processing Systems

This paper focuses on MDPs with linearly realizable optimal Q-functionQ?.

artificial intelligence, arxivpreprintarxiv, machine learning, (15 more...)

Neural Information Processing Systems

Feb-9-2026, 18:43:37 GMT

Conferences PDF

Country:
- Asia
  - Japan > Honshū
    - Tōhoku (0.04)
  - Middle East > Jordan (0.04)

Genre:
- Research Report (0.46)

Industry:
- Leisure & Entertainment (0.68)
- Media > Television (0.68)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning (1.00)
  - Representation & Reasoning (0.94)

Duplicate Docs Excel Report

Title
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Similar Docs Excel Report more

Title	Similarity	Source
None found