Unbounded Dynamic Programming via the Q-Transform

• Tác giả: Qingyin Ma, John Stachurski, Alexis Akira Toda
• Ngôn ngữ: eng
• Ký hiệu phân loại: 005.116 +*Constraint programming
• Thông tin xuất bản: 2020
• Bộ sưu tập: Metadata
• ID: 165699

Tóm tắt

Comment: arXiv admin note: text overlap with arXiv:1911.13025We propose a new approach to solving dynamic decision problems with unbounded rewards based on the transformations used in Q-learning. In our case, the objective of the transform is to convert an unbounded dynamic program into a bounded one. The approach is general enough to handle problems for which existing methods struggle, and yet simple relative to other techniques and accessible for applied work. We show by example that many common decision problems satisfy our conditions.