Paradox of AlphaZero: Strategic vs. Optimal Plays.

Ze-Li Dou Liran Ma Khiem Nguyen Kien X. Nguyen

Published in: IPCCC (2020)

Keyphrases

learning algorithm
reinforcement learning
dynamic programming
closed form
decision making
data sets
case study
optimal control
optimal design
search engine
information systems
feature selection
information technology
exhaustive search
globally optimal
asymptotically optimal