An Introduction of mini-AlphaStar
This work provides an open-source, scaled-down implementation for researchers studying reinforcement learning in complex environments like StarCraft II, but it is incremental as it modifies hyperparameters without introducing new methods.
The authors tackled the challenge of replicating AlphaStar's success in StarCraft II by creating a mini-scaled version called mini-AlphaStar, which achieved a high win rate of 99.8% against human players in the original work.
StarCraft II (SC2) is a real-time strategy game in which players produce and control multiple units to fight against opponent's units. Due to its difficulties, such as huge state space, various action space, a long time horizon, and imperfect information, SC2 has been a research hotspot in reinforcement learning. Recently, an agent called AlphaStar (AS) has been proposed, which shows good performance, obtaining a high win rate of 99.8% against human players. We implemented a mini-scaled version of it called mini-AlphaStar (mAS) based on AS's paper and pseudocode. The difference between AS and mAS is that we substituted the hyper-parameters of AS with smaller ones for mini-scale training. Codes of mAS are all open-sourced (https://github.com/liuruoze/mini-AlphaStar) for future research.