Strategic Deep Learning
Abstract
This chapter studies strategic interactions among intelligent agents. Neural architectures become strategic choices. Multi-agent tensor-graph learning is developed. Mean-field-type games govern agent populations. Human-machine co-intelligence is formalized across autonomy levels. Stackelberg structures organize control. Communication equilibria are analyzed under cost. Risk is captured via expectile value-at-risk. Agentic machine intelligence is defined rigorously. The chapter frames deep learning as a strategic, societal system.
Fields of Study & Subjects
Artificial Intelligence Applications
Neural Networks and Applications
Artificial Intelligence in Games
Publication details
- Journal / source
- Chapman & Hall/CRC eBooks
- Pages
- 213–264
- Publication date
- 6 February 2026
- Language
- EN
- Document type
- Book chapter