Uncertainty-Balanced Preference Planning

Researchers introduce UBP2, a model-based approach for efficient preference-based reinforcement learning. UBP2 actively directs exploration by reasoning over uncertainties in reward, dynamics, and value functions.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementJun 17, 2026, 05:54 PM 90%

   Researchers Introduce UBP2 for Efficient Preference-Based Reinforcement Learning

   Researchers introduce UBP2, a model-based approach for efficient preference-based reinforcement learning. UBP2 actively directs exploration by reasoning over uncertainties in reward, dynamics, and value functions.

   Read the full story →