SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

Description

Summary

• an efficient deep reinforcement learning agent mastering the game of StarCraft II AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve in complex Real-Time Strategy (RTS) games.
• Weber (2010) , where most bots are built with heuristic rules together with search methods AlphaStar is the first end-to-end learning algorithm for StarCraft II full game that reaches GrandMaster level.
• Besides the sparse win/loss reward, there is a second type of reward based on strategy statistic z.
• The strategy statistic z are extracted from human replays which encode constructed buildings and units present during a game.
• First, after a frame is observed, SCC needs to process the observation as a valid input for the policy network and then perform a forward inference, which takes about 100ms on average.