Complexity as Advantage: A Regret-Based Perspective on Emergent Structure
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
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 LearningvalidBandits with Knapsacks beyond the Worst Case
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 BanditsBandits with Knapsacks beyond the Worst-Case
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 BanditsEmergent Generalization by Representation Learning in Artificial Neural Networks
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 LearningGap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
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