Paper Info
Title
StarCraft II: A New Challenge for Reinforcement Learning.
Abstract
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. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures.
Year
Venue
Field
2017
arXiv: Learning
Suite,Computer science,Challenging environment,Artificial intelligence,Learning environment,Perfect information,Artificial neural network,State space,Machine learning,Python (programming language),Reinforcement learning
DocType
Volume
Citations 
Journal
abs/1708.04782
46
PageRank 
References 
Authors
1.67
20
25
Name
Order
Citations
PageRank
Oriol Vinyals19419418.45
Timo Ewalds2461.67
Sergey Bartunov3462.34
Petko Georgiev4702.74
Alexander Vezhnevets527410.85
Michelle Yeo6462.01
Alireza Makhzani7553.71
Heinrich Küttler8523.78
John Agapiou9462.01
Julian Schrittwieser101175.20
john quan1133913.28
Stephen Gaffney12462.01
Stig Petersen13232995.83
Karen Simonyan1412058446.84
Tom Schaul1591679.40
hado van hasselt1643231.39
David Silver178252363.86
Timothy P. Lillicrap184377170.65
Kevin Calderone19461.67
Paul Keet20461.67
Anthony Brunasso21461.67
David Lawrence22461.67
Anders Ekermo23461.67
Jacob Repp24461.67
Rodney Tsing25461.67