Preference-based Reinforcement Learning with Finite-Time Guarantees
–Neural Information Processing Systems
We first show that a unique optimal policy may not exist if preferences over trajectories are deterministic for PbRL.
Neural Information Processing Systems
Feb-10-2026, 16:31:00 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- North America
- Canada (0.04)
- United States
- California (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Asia > Middle East
- Genre:
- Research Report > New Finding (0.69)
- Technology: