AlphaStar learned from both human and agent games using deep neural networks and multi-agent reinforcement learning.

Format Online paper / PDF

Location PART 3 - THE THIRD AXIS CHAPTER 12: DARK INFORMATION Move 78

"AlphaStar learned from both human and agent games using deep neural networks and multi-agent reinforcement learning."

The published system used human and agent gameplay data within a league of continually adapting strategies and counter-strategies represented by deep neural networks.

View Source

Source title Grandmaster level in StarCraft II using multi-agent reinforcement learning

Source authors Oriol Vinyals; Igor Babuschkin; Wojciech M. Czarnecki; et al.

Source year 2019

Confidence high

Importance mid