paper-with-me

Papers

Complexity as Advantage: A Regret-Based Perspective on Emergent Structure

2025-11-06 · Oshri Naparstek arxiv

We introduce Complexity as Advantage (CAA), a framework that defines the complexity of a system relative to a family of observers. Instead of measuring complexity as an intrinsic property, we evaluate how much predictive regret a system induces for different observers attempting to model it. A system is complex when it is easy for some observers and hard for others, creating an information advantage. We show that this formulation unifies several notions of emergent behavior, including multiscale entropy, predictive information, and observer-dependent structure. The framework suggests that "interesting" systems are those positioned to create differentiated regret across observers, providing a quantitative grounding for why complexity can be functionally valuable. We demonstrate the idea through simple dynamical models and discuss implications for learning, evolution, and artificial agents.

📄 PDF Abstract BibTeX arXiv:2511.04590

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

2020-12-03 · NeurIPS 2020 12 · Michael Dennis, Natasha Jaques, Eugene Vinitsky, Alexandre Bayen 외

A wide range of reinforcement learning (RL) problems - including robustness, transfer learning, unsupervised RL, and emergent complexity - require specifying a distribution of tasks or environments in which a policy will…

Reinforcement Learning (RL)Transfer Learningvalid

Bandits with Knapsacks beyond the Worst Case

2021-12-01 · NeurIPS 2021 12 · Karthik Abinav Sankararaman, Aleksandrs Slivkins

Bandits with Knapsacks (BwK) is a general model for multi-armed bandits under supply/budget constraints. While worst-case regret bounds for BwK are well-understood, we present three results that go beyond the worst-case …

Multi-Armed Bandits

Bandits with Knapsacks beyond the Worst-Case

2020-02-01 · Karthik Abinav Sankararaman, Aleksandrs Slivkins

Bandits with Knapsacks (BwK) is a general model for multi-armed bandits under supply/budget constraints. While worst-case regret bounds for BwK are well-understood, we present three results that go beyond the worst-case …

Multi-Armed Bandits

Emergent Generalization by Representation Learning in Artificial Neural Networks

2026-07-11 · Hardik Rajpal, Dan Goodman arxiv

Dimensionality reduction has proven powerful for identifying neural manifolds, which are low-dimensional structures underlying high-dimensional neural activity. These low-dimensional representations have improved the int…

Dimensionality ReductionRepresentation Learning

Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition

2024-10-10 · Zhong Zheng, Haochen Zhang, Lingzhou Xue

We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et al. 2020) and Q-EarlySettled-Advantage …

Q-Learning