Article

Regret Is Weighted Forgetting

2026-03-19

Abstract excerpt

How much of an agent's regret comes from a bad representation, and how much from a bad policy? This paper gives an exact answer. For a fixed representation M and a finite evaluation distribution over history-test pairs, the minimum average normalized regret over all M-based policies equals the minimum margin-weighted deletion cost needed to make the optimal bet single-valued on each representation-test cell (M(h),...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5a15e780-e770-5586-8ae1-bd1fb1ae2c2c
DOI: 10.20944/preprints202603.1546.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Regret Is Weighted ForgettingDOI 10.20944/preprints202603.1546.v1Read

Regret Is Weighted ForgettingSemantic proximity Read

Reward-predictive representations generalize across tasks in reinforcement learningSemantic proximity Read

The Value of AbstractionSemantic proximity Read

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learningSemantic proximity Read

Compositional clustering in task structure learningSemantic proximity Read

On the computational principles underlying human explorationSemantic proximity Read

Computation noise promotes cognitive resilience to adverse conditions during decision-makingSemantic proximity Read

Connecting Exploration, Generalization, and Planning in Correlated TreesSemantic proximity Read

Multi-Agent based Dynamic Anchors for Interpretation of Deep Learning ClassifiersSemantic proximity Read

Why Compression Creates Intelligence: The Architecture of Experience in Large ModelsSemantic proximity Read

Behavioural Transparency in Multi-Agent RL: Strategic Decoupling and the Economic Optimisation of Tactical ShocksSemantic proximity Read

The Naive Utility Calculus as a unified, quantitative framework for action understandingSemantic proximity Read