Optimal training for adversarial games

DOI10.1007/s10472-020-09724-0zbMath1473.35583OpenAlexW3118372973MaRDI QIDQ2043435

Ovidiu Calin

Publication date: 2 August 2021

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10472-020-09724-0

zbMATH Keywords

Hamiltonian systemadversarial gamesoptimal training timesimultaneous gradient descent

Mathematics Subject Classification ID

2-person games (91A05) Existence of solutions for minimax problems (49J35) Rationality and learning in game theory (91A26) Dynamical systems in optimization and economics (37N40) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) PDEs in connection with control and optimization (35Q93)

Uses Software

• Agent57

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Methods of applied mathematics with a MATLAB overview
• Heat kernels for elliptic and sub-elliptic operators. Methods and techniques
• Investigating the Limits of Monte-Carlo Tree Search Methods in Computer Go
• Deep Learning Architectures