AlphaStar explained: Grandmaster level in StarCraft II with multi-agent RL

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=eZCI7zu_DlM


StarCraft II
Game:
StarCraft II (2010)
Category:
Let's Play
Duration: 2:10:12
7,012 views
145

For slides and more information on the paper, visit https://aisc.ai.science/events/2019-12-09

Discussion lead: Gordon Gibson
Discussion facilitator(s): Alok Deshpande, Xiyang Chen

Correction: in the video it was stated that 128 TPU's are used for training. The actual number was 32.

From the official website:

TL;DR: AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. This January, a preliminary version of AlphaStar challenged two of the world's top players in StarCraft II, one of the most enduring and popular real-time strategy video games of all time. Since then, we have taken on a much greater challenge: playing the full game at a Grandmaster level under professionally approved conditions.

Our new research differs from prior work in several key regards:
1. AlphaStar now has the same kind of constraints that humans play under – including viewing the world through a camera, and stronger limits on the frequency of its actions* (in collaboration with StarCraft professional Dario “TLO” Wünsch).
2. AlphaStar can now play in one-on-one matches as and against Protoss, Terran, and Zerg – the three races present in StarCraft II. Each of the Protoss, Terran, and Zerg agents is a single neural network.
3. The League training is fully automated, and starts only with agents trained by supervised learning, rather than from previously trained agents from past experiments.
4. AlphaStar played on the official game server, Battle.net, using the same maps and conditions as human players. All game replays are available here.



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-02-11Attention is not not explanation + Character Eyes: Seeing Language through Character-Level Taggers |
2020-02-10Single Headed Attention RNN: Stop Thinking With Your Head | AISC
2020-01-27Identifying Big ML product opportunities inside Big organizations | AISC
2020-01-23Machine Learning in Cyber Security, Overview | AISC
2020-01-22BottleSum: Unsupervised & Self-supervised Sentence Summarization w/ Information Bottleneck Principle
2020-01-20A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural
2020-01-13Plug and Play Language Models: A Simple Approach to Controlled Text Generation | AISC
2020-01-08Overview of Modern Anomaly and Novelty Detection | AISC
2020-01-06Annotating Object Instances With a Polygon RNN | AISC
2019-12-11Predicting translational progress in biomedical research | AISC
2019-12-09AlphaStar explained: Grandmaster level in StarCraft II with multi-agent RL
2019-12-04How Can We Be So Dense? The Benefits of Using Highly Sparse Representations | AISC
2019-12-02[RoBERT & ToBERT] Hierarchical Transformers for Long Document Classification | AISC
2019-11-25[OpenAI] Solving Rubik's Cube with a Robot Hand | AISC
2019-11-18Top-K Off-Policy Correction for a REINFORCE Recommender System | AISC
2019-11-13Overview of Unsupervised & Semi-supervised learning | AISC
2019-11-11Building products for Continous Delivery in Machine Learning | AISC
2019-11-06[WeightWatcher] Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory
2019-11-04Defending Against Fake Neural News | AISC
2019-10-28[RecSys Challenge 2019 2nd Place] Robust Contextual Models for In-Session Personalization | AISC
2019-10-23Deep learning enables rapid identification of potent DDR1 kinase inhibitors | AISC


Tags:
alphastar
starcraft
reinforcement learning
deep learning
ai
deepmind
machinlearning


Other Statistics

StarCraft II Statistics For LLMs Explained - Aggregate Intellect - AI.SCIENCE

LLMs Explained - Aggregate Intellect - AI.SCIENCE presently has 7,012 views for StarCraft II across 1 video, with the game making up 2 hours of published video on his channel. This is less than 0.48% of StarCraft II video content that LLMs Explained - Aggregate Intellect - AI.SCIENCE has uploaded to YouTube.