Multiagent Deep Reinforcement Learning Algorithms in StarCraft II: A Review by Yanyan Li, Yijun Wang, Yiwei Zhou

Subjects: Get full text

SC2EGSet: StarCraft II Esport Replay and Game-state Dataset by Andrzej Białecki, Natalia Jakubowska, Paweł Dobrowolski, Piotr Białecki, Leszek Krupiński, Andrzej Szczap, Robert Białecki, Jan Gajewski

“…Our dataset contains replays from major and premiere StarCraft II tournaments since 2016. We processed 55 “replaypacks” that contained 17930 files with game-state information. …”
Get full text

SC-Phi2: A Fine-Tuned Small Language Model for StarCraft II Build Order Prediction by Muhammad Junaid Khan, Gita Sukthankar

Subjects: “…StarCraft II…”
Get full text

SA-MARL: Novel Self-Attention-Based Multi-Agent Reinforcement Learning With Stochastic Gradient Descent by Rabbiya Younas, Hafiz Muhammad Raza Ur Rehman, Ingyu Lee, Byung-Won On, Sungwon Yi, Gyu Sang Choi

Subjects: Get full text

SC-MAIRL: Semi-Centralized Multi-Agent Imitation Reinforcement Learning by Paul Brackett, Siming Liu, Yan Liu

Subjects: Get full text

Co-Evolving Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation by Ayesha Siddiqua, Siming Liu, Ayesha Siddika Nipu, Anthony Harris, Yan Liu

Subjects: Get full text

GHQ: grouped hybrid Q-learning for cooperative heterogeneous multi-agent reinforcement learning by Xiaoyang Yu, Youfang Lin, Xiangsen Wang, Sheng Han, Kai Lv

Subjects: Get full text

Robustness of performance during domain change in an esport: A study of within-expertise transfer. by Joe Thompson, Justin W O'Camb, Robin C A Barrett, Scott Harrison, Mark R Blair

“…Here we examine skill maintenance in StarCraft 2, a video game of skills which undergoes frequent changes due to updates and includes a variety of gameplay options. …”
Get full text

Computerspil og læring by Lasse Juel Larsen

“…Artikel tager afsæt i Gregory Batesons læringsteori og læser denne igennem det kommercielle computerspil StarCraft 2 fra Blizzard Intertainment. Batesons læringsteori vil ikke alene blive gennemgået, men også udvidet og perspektiveret.  …”
Get full text

Computerspil og læring by Lasse Juel Larsen

“…Artikel tager afsæt i Gregory Batesons læringsteori og læser denne igennem det kommercielle computerspil StarCraft 2 fra Blizzard Intertainment. Batesons læringsteori vil ikke alene blive gennemgået, men også udvidet og perspektiveret.  …”
Get full text

Over the hill at 24: persistent age-related cognitive-motor decline in reaction times in an ecologically valid video game task begins in early adulthood. by Joseph J Thompson, Mark R Blair, Andrew J Henrey

“…The present study investigates age-related changes in cognitive motor performance through adolescence and adulthood in a complex real world task, the real-time strategy video game StarCraft 2. In this paper we analyze the influence of age on performance using a dataset of 3,305 players, aged 16-44, collected by Thompson, Blair, Chen & Henrey [1]. …”
Get full text

DESEM: Depthwise Separable Convolution-Based Multimodal Deep Learning for In-Game Action Anticipation by Changhyun Kim, Jinsoo Bae, Insung Baek, Jaeyoon Jeong, Young Jae Lee, Kiwoong Park, Sang Heun Shim, Seoung Bum Kim

“…Because RTS games like StarCraft II are real-time, players have a very limited time to choose how to develop their strategy. …”
Get full text

Association between real-time strategy video game learning outcomes and pre-training brain white matter structure: preliminary study by Paulina Lewandowska, Natalia Jakubowska, Nikodem Hryniewicz, Rafał Prusinowski, Bartosz Kossowski, Aneta Brzezicka, Natalia Kowalczyk-Grębska

“…The aim of this preliminary study was to investigate whether acquisition of cognitive-motor skills from the real-time strategy video game (StarCraft II) is associated with pre-training measures of brain white matter integrity. …”
Get full text

A Novel and Efficient Influence-Seeking Exploration in Deep Multiagent Reinforcement Learning by Byunghyun Yoo, Devarani Devi Ningombam, Sungwon Yi, Hyun Woo Kim, Euisok Chung, Ran Han, Hwa Jeon Song

“…We evaluate the proposed exploration method on a set of StarCraft II micromanagement as well as modified predator-prey tasks. …”
Get full text

Warm-Starting Networks for Sample-Efficient Continuous Adaptation to Parameter Perturbations in Multi-Agent Reinforcement Learning by Huang, Vivian

“…Therefore, this thesis work details the design and implementation of a MARL framework that facilitates the training of robust agents which are adaptive to perturbations in a multi-agent, StarCraft II-based real-time strategy game such that the features that most affect game balance can be determined. …”
Get full text

Generating individual intrinsic reward for cooperative multiagent reinforcement learning by Haolin Wu, Hui Li, Jianwei Zhang, Zhuang Wang, Jianeng Zhang

“…Experimental results in the StarCraft II micromanagement benchmark prove that the proposed algorithm can increase learning efficiency and improve policy performance.…”
Get full text

Deep coordination graphs by Boehmer, W, Kurin, V, Whiteson, S

“…We show that DCG can solve predator-prey tasks that highlight the relative overgeneralization pathology, as well as challenging StarCraft II micromanagement tasks.…”

The Important Role of Global State for Multi-Agent Reinforcement Learning by Shuailong Li, Wei Zhang, Yuquan Leng, Xiaohui Wang

“…We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. …”
Get full text

Trajectory Based Prioritized Double Experience Buffer for Sample-Efficient Policy Optimization by Shengxiang Li, Ou Li, Guangyi Liu, Siyuan Ding, Yijie Bai

“…Reinforcement learning has recently made great progress in various challenging domains such as board game of Go and MOBA game of StarCraft II. Policy gradient based reinforcement learning method has become the mainstream due to its effectiveness and simplicity both in discrete and continuous scenarios. …”
Get full text

A Pattern Mining Approach to Study Strategy Balance in RTS Games by Bosc, Guillaume, Boulicaut, Jean-Francois, Raissi, Chedy, Kaytoue, Mehdi, Tan, Philip

“…We experiment with our algorithm on StarCraft II historical data, played professionally as an electronic sport.…”
Get full text