AlphaStar: An Evolutionary Computation Perspective

5 Feb 2019 · Kai Arulkumaran, Antoine Cully, Julian Togelius ·

In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI. AlphaStar draws on many areas of AI research, including deep learning, reinforcement learning, game theory, and evolutionary computation (EC). In this paper we analyze AlphaStar primarily through the lens of EC, presenting a new look at the system and relating it to many concepts in the field. We highlight some of its most interesting aspects-the use of Lamarckian evolution, competitive co-evolution, and quality diversity. In doing so, we hope to provide a bridge between the wider EC community and one of the most significant AI systems developed in recent times.

Code

Add Remove Mark official

SpinazieSin/scared_citizen_simulati…

5

Tasks

Add Remove

Reinforcement Learning (RL)

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

1x1 Convolution • Absolute Position Encodings • Accumulating Eligibility Trace • Adam • Additive Attention • AlphaStar • Average Pooling • Batch Normalization • Bottleneck Residual Block • BPE • Convolution • Dense Connections • Dropout • Feedforward Network • Global Average Pooling • GLU • Kaiming Initialization • Label Smoothing • Layer Normalization • Linear Layer • LSTM • Max Pooling • Multi-Head Attention • Pointer Network • Position-Wise Feed-Forward Layer • ReLU • Residual Block • Residual Connection • ResNet • Scaled Dot-Product Attention • Scatter Connection • Sigmoid Activation • Softmax • Tanh Activation • TD Lambda • Transformer • V-trace