The Asymptotic Cost of Complexity

• Tác giả: Martin W Cripps
• Ngôn ngữ: eng
• Ký hiệu phân loại: 512.74 Algebraic number theory
• Thông tin xuất bản: 2024
• Bộ sưu tập: Metadata
• ID: 203865

Tóm tắt

We propose a measure of learning efficiency for non-finite state spaces. We characterize the complexity of a learning problem by the metric entropy of its state space. We then describe how learning efficiency is determined by this measure of complexity. This is, then, applied to two models where agents learn high-dimensional states.