On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

Aug-16-2025, 14:01:47 GMT–Neural Information Processing Systems

Our analyses indicate that the explorability or reachability assumptions, previously made for the latter two settings, are not necessary statistically for reward-free exploration.

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

Neural Information Processing Systems

Aug-16-2025, 14:01:47 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America > United States
  - Illinois > Champaign County
    - Urbana (0.04)
  - Michigan (0.04)

Genre:
- Research Report > New Finding (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Reinforcement Learning (0.46)
    - Representation & Reasoning (1.00)
  - Data Science (0.67)

Duplicate Docs Excel Report

Title
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL Jinglin Chen

Similar Docs Excel Report more

Title	Similarity	Source
None found