Preference-based Reinforcement Learning with Finite-Time Guarantees

Aug-16-2025, 18:01:27 GMT–Neural Information Processing Systems

We first show that a unique optimal policy may not exist if preferences over trajectories are deterministic for PbRL.

algorithm, complexity, trajectory, (13 more...)

Neural Information Processing Systems

Aug-16-2025, 18:01:27 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- North America
  - Canada (0.04)
  - United States
    - California (0.04)
    - Pennsylvania > Allegheny County
      - Pittsburgh (0.04)

Genre:
- Research Report > New Finding (0.94)

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