Doina Precup

Reinforcement-learning researcher

Many Builders reference roster

Research on reinforcement learning, planning under uncertainty, and how learning systems retain and adapt knowledge.

Many Builders reference → Safety & alignment coverage →

Writing and research by Doina Precup

2 supplied byline matches

These articles, papers and essays carry Doina Precup in the source-supplied author field. Verify the definitive byline and text at the original publisher.

arXiv cs.AI3 August 2026

Analytic Planning under Uncertainty with Moment Closure — open the original publisher

By Shishir Sharma, Doina Precup

Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable. Consequently, modern deep reinforcement learning has largely retreated to either stochastic sampling, which introduces significant target variance, or deterministic point estimates that igno

Research RegulationEnvironment

Evidence record Cite Share

arXiv6 July 2026

To Retain or to Adapt? Generalizing Continual Learning — open the original publisher

By Giulia Lanzillotta, Mandana Samiei, Doina Precup, Razvan Pascanu, Claire Vernade

The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, often unstated assumption: that a lifelong learner should approximate the Joint-Task Learning (JTL) solution and retain all previously acquired knowledge. We challenge this retention-centered premise, arguing that in non-stationary environments prioritizing retention can impede real-time adaptation. Shifting the focus to the Average Lifelong Error (A

Research Environment

Evidence record Cite Share