About

Real-Time Strategy (RTS) tasks involve training an agent to play video games with continuous gameplay and high-level macro-strategic goals such as map control, economic superiority and more.

( Image credit: Multi-platform Version of StarCraft: Brood War in a Docker Container )

Benchmarks

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Subtasks

Datasets

Latest papers with code

Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games

5 Oct 2020vwxyzjn/action-guidance

Training agents using Reinforcement Learning in games with sparse rewards is a challenging problem, since large amounts of exploration are required to retrieve even the first reward.

REAL-TIME STRATEGY GAMES

4
05 Oct 2020

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

25 Jun 2020vwxyzjn/invalid-action-masking

Specifically, our experiments show that invalid action masking scales well when the space of invalid actions is large, while the common approach of giving negative rewards for invalid actions will fail.

REAL-TIME STRATEGY GAMES

12
25 Jun 2020

The StarCraft Multi-Agent Challenge

11 Feb 2019oxwhirl/pymarl

In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap.

SMAC STARCRAFT STARCRAFT II

759
11 Feb 2019

Constrained optimization under uncertainty for decision-making problems: Application to Real-Time Strategy games

3 Jan 2019richoux/microrts-uncertainty

However, few Constraint Programming formalisms can deal with both optimization and uncertainty at the same time, and none of them are convenient to model problems we tackle in this paper.

COMBINATORIAL OPTIMIZATION DECISION MAKING REAL-TIME STRATEGY GAMES

3
03 Jan 2019

StarAlgo: A Squad Movement Planning Library for StarCraft using Monte Carlo Tree Search and Negamax

29 Dec 2018Games-and-Simulations/StarAlgo

Real-Time Strategy (RTS) games have recently become a popular testbed for artificial intelligence research.

STARCRAFT

14
29 Dec 2018

Macro action selection with deep reinforcement learning in StarCraft

2 Dec 2018Bilibili/LastOrder

These rules are not scalable and efficient enough to cope with the enormous yet partially observed state space in the game.

STARCRAFT

54
02 Dec 2018

Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders

30 Nov 2018TeamSAIDA/SAIDA

StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research for both micro-level unit control and macro-level strategic decision making.

DECISION MAKING STARCRAFT

72
30 Nov 2018

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

ICLR 2018 facebookresearch/starcraft_defogger

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games.

STARCRAFT

27
30 Nov 2018

TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game

19 Sep 2018Tencent/TStarBots

Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.

DECISION MAKING STARCRAFT STARCRAFT II

65
19 Sep 2018

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

15 Aug 2018cair/DeepRTS

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games.

STARCRAFT STARCRAFT II

92
15 Aug 2018