4 papers
The Intervention Gap in Latent World Models
Donna Vakalis
Planning-time intervention fidelity is a distinct, measurable property of a learned world model: whether the model's own open-loop transitions move task variables the way matched e…
What a World Model Represents Is Three Questions
Donna Vakalis
World models learn task-relevant information through many routes: observation reconstruction, recurrent state, temporal filtering, and explicit task supervision. Different routes c…
Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models
Donna Vakalis
World-model evaluation for model-based reinforcement learning typically asks whether the learned model predicts reward and value well, which can leave planning-relevant errors in t…
In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior
Anaïs Berkes, Vincent Taboga, Donna Vakalis +2
In-context reinforcement learning (ICRL) promises fast adaptation to unseen environments without parameter updates, but current methods either cannot improve beyond the training di…