Pith.

Machine Learning · arXiv:2012.13169 v3 · submitted 24 Dec 2020

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

Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi

show 4 more authors

Jujie He, Chao Gao, Haitao Long, Quan Yuan

The paper says

“With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event.”

from the abstract · picked out as the main claim by a classifier

Pith says

Pith has not reviewed this paper.

Get a Pith Review, $5

Reviews

Reviews by people

No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

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. However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. We propose a deep reinforcement learning agent, StarCraft Commander (SCC). With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-09-23 · no language-model review

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.07 · states limitation 0.12 · human participants 0.39 · controlled comparison 0.21 · randomized assignment 0.01 · states quantitative result 0.20 · compares with prior results 0.92 · mentions code or data availability 0.06

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v3). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
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. background 1.00 0.05 0.04 asserted 1.00
However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. background 0.59 0.09 0.03 asserted 1.00
We propose a deep reinforcement learning agent, StarCraft Commander (SCC). contribution 0.97 0.84 0.07 asserted 0.93
With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. result 0.99 0.92 0.69 asserted 1.00
Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. result 1.00 0.91 0.18 asserted 1.00
In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game. contribution 0.77 0.67 0.09 asserted 0.79

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.85

What was examined, and what was not

Sources read

  • arXiv listing abstract v3

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,886 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Cited by 1 Pith paper
How the literature uses it

2 arXiv papers cite this in 2 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 1 sentence without a confident label

Uses its method or tool 1 paper

What it cites · 3 sentences without a confident label

Uses the method or tool of 2 papers
  • Starting from the policy provided by the supervised training stage, we apply the Proximal Policy Optimization (PPO) [ref] to further improve the performance of SCC based on agent versus agent games.

    Proximal Policy Optimization Algorithms · Learning Algorithm · 1.00

  • Separate value functions and advantages are computed for each reward, and the generalized advantage estimation (GAE) [ref] is applied to balance the trade-off between the bias and variance of the advantage estimation.

    High-Dimensional Continuous Control Using Generalized Advantage Estimation · Learning Algorithm · 1.00

Cites as background 10 papers

Challenges and discussion

Know something about this paper? Leave a comment.

No comments yet.

Sign in to comment