Verifiable Reinforcement Learning via Policy Extraction

Osbert Bastani, Yewen Pu, Armando Solar-Lezama

Feb-15-2026, 01:51:09 GMT–Neural Information Processing Systems

Trajectoriestakenby , left : s 7! left, and right : s 7! rightareshownas dashededges, rededges, andgreenedges, respectively. Let ={ left : s 7! left, right : s 7! right}, andletg( )= Es d( )[g(s, )]bethe 0-1 loss.

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

Neural Information Processing Systems

Feb-15-2026, 01:51:09 GMT

Conferences PDF

Add feedback

Country:
- North America
  - Canada > Quebec
    - Montreal (0.04)
  - United States
    - California (0.04)
    - Massachusetts > Middlesex County
      - Cambridge (0.05)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning (0.94)

Duplicate Docs Excel Report

Title
Verifiable Reinforcement Learning via Policy Extraction
Verifiable Reinforcement Learning via Policy Extraction

Similar Docs Excel Report more

Title	Similarity	Source
None found