Doina Precup

Target variance in reinforcement learning can be drastically reduced by analytically propagating uncertainty without restrictive policy structures.

Adaptive temporal discounting can dramatically enhance reinforcement learning's efficiency and flexibility, outperforming traditional fixed discount methods.

Retaining past knowledge can actually impede real-time adaptation in dynamic environments, leading to a new framework for optimizing continual learning.

Active exploration can dramatically enhance adults' ability to reason about complex causal relationships, but even with this advantage, they still struggle compared to simpler tasks.

Forget fixed teams: this new reinforcement learning framework lets agents spawn new teammates on the fly, unlocking dynamic strategies previously impossible.