TightRegretBoundsforModel-Based Reinforcement LearningwithGreedyPolicies

Feb-11-2026, 17:45:22 GMT–Neural Information Processing Systems

The results are based on anovelanalysis ofreal-time dynamic programming, thenextended tomodel-based RL.Specifically,wegeneralize existing algorithms that perform full-planning to act by 1-step planning.

artificial intelligence, machine learning, skt, (17 more...)

Neural Information Processing Systems

Feb-11-2026, 17:45:22 GMT

Conferences PDF

Add feedback

Country:
- Asia > Middle East
  - Israel (0.05)
- North America
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
  - United States > Massachusetts
    - Middlesex County > Belmont (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning (1.00)
  - Representation & Reasoning (0.89)