High-Level Strategy Selection under Partial Observability in StarCraft: Brood War

2018-11-21 · Jonas Gehring, Da Ju, Vegard Mella, Daniel Gant, Nicolas Usunier, Gabriel Synnaeve

We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective strategy. Here, a good strategy successfully counters the opponent's current and possible future strategies which can only be estimated using partial observations. We investigate whether we can utilize the full game state information during training time (in the form of an auxiliary prediction task) to increase performance. Experiments carried out within a StarCraft: Brood War bot against strong community bots show substantial win rate improvements over a fixed-strategy baseline and encouraging results when learning with the auxiliary task.

📄 PDF Abstract BibTeX arXiv:1811.08568

Code (0)

등록된 구현이 없습니다.

Tasks

Real-Time Strategy Gamesreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)StarcraftVocal Bursts Intensity Prediction

From Big to Small: Adaptive Learning to Partial-Set Domains

2022-03-14 · Zhangjie Cao, Kaichao You, Ziyang Zhang, Jianmin Wang 외

Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared acro…

Domain Adaptation Partial Domain Adaptation

Partial Information in a Mean-Variance Portfolio Selection Game

2023-12-07 · Yu-Jui Huang, Li-Hsien Sun

This paper considers finitely many investors who perform mean-variance portfolio selection under relative performance criteria. That is, each investor is concerned about not only her terminal wealth, but how it compares …

Mean-variance portfolio selection under partial information with drift uncertainty

2019-01-10 · Jie Xiong, Zuo Quan Xu, Jiayu Zheng

In this paper, we study the mean-variance portfolio selection problem under partial information with drift uncertainty. First we show that the market model is complete even in this case while the information is not compl…

GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D

2024-05-20 · Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori, Milad Cheraghalikhani 외

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). U…

Knowledge Distillation Self-Supervised Learning

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning

2023-03-18 · CVPR 2024 1 · Shiyu Tian, Hongxin Wei, Yiqun Wang, Lei Feng

Partial-label learning (PLL) is an important weakly supervised learning problem, which allows each training example to have a candidate label set instead of a single ground-truth label. Identification-based methods have …

Partial Label Learning Weakly-supervised Learning