Worst-Case Regret Bounds for Exploration via Randomized Value Functions

Oct-2-2025, 15:29:10 GMT–Neural Information Processing Systems

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning.

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

Neural Information Processing Systems

Oct-2-2025, 15:29:10 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe > United Kingdom
  - England
    - Greater London > London (0.04)
    - Oxfordshire > Oxford (0.04)
- North America > Canada (0.04)

Genre:
- Overview (0.34)
- Research Report (0.34)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models (0.93)
    - Reinforcement Learning (0.91)
  - Representation & Reasoning > Uncertainty (0.68)