StarCraft II: A New Challenge for Reinforcement Learning

16 Aug 2017Oriol VinyalsTimo EwaldsSergey BartunovPetko GeorgievAlexander Sasha VezhnevetsMichelle YeoAlireza MakhzaniHeinrich KüttlerJohn AgapiouJulian SchrittwieserJohn QuanStephen GaffneyStig PetersenKaren SimonyanTom SchaulHado van HasseltDavid SilverTimothy LillicrapKevin CalderonePaul KeetAnthony BrunassoDavid LawrenceAnders EkermoJacob ReppRodney Tsing

This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Starcraft II CollectMineralShards FullyConv LSTM Max Score 137 # 1
Starcraft II MoveToBeacon FullyConv LSTM Max Score 35 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet