Search

Your search keyword '"Guo, Qingwei"' showing total 299 results
Start Over Author "Guo, Qingwei"
299 results on '"Guo, Qingwei"'

7. TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game

Author

Han, Lei, Xiong, Jiechao, Sun, Peng, Sun, Xinghai, Fang, Meng, Guo, Qingwei, Chen, Qiaobo, Shi, Tengfei, Yu, Hongsheng, Wu, Xipeng, and Zhang, Zhengyou

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

StarCraft, one of the most difficult esport games with long-standing history of professional tournaments, has attracted generations of players and fans, and also, intense attentions in artificial intelligence research. Recently, Google's DeepMind announced AlphaStar, a grandmaster level AI in StarCraft II that can play with humans using comparable action space and operations. In this paper, we introduce a new AI agent, named TStarBot-X, that is trained under orders of less computations and can play competitively with expert human players. TStarBot-X takes advantage of important techniques introduced in AlphaStar, and also benefits from substantial innovations including new league training methods, novel multi-agent roles, rule-guided policy search, stabilized policy improvement, lightweight neural network architecture, and importance sampling in imitation learning, etc. We show that with orders of less computation scale, a faithful reimplementation of AlphaStar's methods can not succeed and the proposed techniques are necessary to ensure TStarBot-X's competitive performance. We reveal all technical details that are complementary to those mentioned in AlphaStar, showing the most sensitive parts in league training, reinforcement learning and imitation learning that affect the performance of the agents. Most importantly, this is an open-sourced study that all codes and resources (including the trained model parameters) are publicly accessible via \url{https://github.com/tencent-ailab/tleague_projpage}. We expect this study could be beneficial for both academic and industrial future research in solving complex problems like StarCraft, and also, might provide a sparring partner for all StarCraft II players and other AI agents., Comment: 29 pages

Published
2020

9. EBV lytic proteins BZLF1 and BILF1 inhibit the expression of major histocompatibility complex in Raji cells

Author

ZHENG Hongling, GUO Qingwei, ZHANG Wei, ZHANG Yan, HE Xingbo, YE Bing

Subjects
bzlf1, bilf1, major histocompatibility complex ⅱ, major histocompatibility complex ⅰ, Medicine
Abstract

Objective To investigate whether BZLF1 and BILF1 can inhibit the expression of major histocompatibility complex(MHC)molecules in Raji cells during Epstein-Barr virus (EBV) lytic cycle. Methods Reactivation was triggered by treating Raji cells with TPA and NaB. As the marker protein during EBV lytic state, the BZLF1 protein expression was detected by Western blot. The expression of BZLF1 and BILF1 at transcription level was analyzed by RT-qPCR in EBV reactivation. The expression of MHC class Ⅱ and MHC class Ⅰ molecules was analyzed by flow cytometry. After BZLF1 and BILF1 over-expression or gene silencing via siRNA in Raji cells by electroporation, the expression of MHC class Ⅱ and MHC class Ⅰ molecules was detected by flow cytometry and Western blot respectively. Results EBV reactivation can be triggered with TPA and NaB. The BZLF1 and BILF1 gene expression was observed by inducing EBV reactivation in Raji cells. The levels of MHC class Ⅱ and MHC class Ⅰ molecules were down regulated by inducing EBV reactivation or ectopic expression of BZLF1 and BILF1 (P＜0.05). Expression of MHC class Ⅱ and MHC class Ⅰ molecules was restored by specific siRNA. Conclusions BZLF1 and BILF1 down regulate the expression of MHC class Ⅱ and MHC class Ⅰ molecules in EBV reactivation respectively.

Published
2023
Full Text
View/download PDF

10. Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

Author

Ye, Deheng, Liu, Zhao, Sun, Mingfei, Shi, Bei, Zhao, Peilin, Wu, Hao, Yu, Hongsheng, Yang, Shaojie, Wu, Xipeng, Guo, Qingwei, Chen, Qiaobo, Yin, Yinyuting, Zhang, Hao, Shi, Tengfei, Wang, Liang, Fu, Qiang, Yang, Wei, and Huang, Lanxiao

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, our AI agent, called Tencent Solo, can defeat top professional human players in full 1v1 games., Comment: AAAI 2020

Published
2019

29. Dynamic Characteristics of Canard-Controlled Rocket with Deflected Canard

Author

Gao, Xinbao, Chen, Yongchao, Guo, Qingwei, Li, Tianpeng, Kacprzyk, Janusz, Series editor, Pal, Nikhil R., Advisory editor, Bello Perez, Rafael, Advisory editor, Corchado, Emilio S., Advisory editor, Hagras, Hani, Advisory editor, Kóczy, László T., Advisory editor, Kreinovich, Vladik, Advisory editor, Lin, Chin-Teng, Advisory editor, Lu, Jie, Advisory editor, Melin, Patricia, Advisory editor, Nedjah, Nadia, Advisory editor, Nguyen, Ngoc Thanh, Advisory editor, Wang, Jun, Advisory editor, Qiao, Feng, editor, Patnaik, Srikanta, editor, and Wang, John, editor

Published
2018
Full Text
View/download PDF

37. Coalescence of Al0.3CoCrFeNi polycrystalline high-entropy alloy in hot-pressed sintering: a molecular dynamics and phase-field study.

Author

Guo, Qingwei, Hou, Hua, Wang, Kaile, Li, Muxi, Liaw, Peter K., and Zhao, Yuhong

Subjects
MOLECULAR dynamics, YOUNG'S modulus, SINTERING, TENSILE tests
Abstract

Existing hot sintering models based on molecular dynamics focus on single-crystal alloys. This work proposes a new multiparticle model based on molecular dynamics to investigate coalescence kinetics during the hot-pressed sintering of a polycrystalline Al0.3CoCrFeNi high-entropy alloy. The accuracy and effectiveness of the multiparticle model are verified by a phase-field model. Using this model, it is found that when the particle contact zones undergo pressure-induced evolution into exponential power creep zones, the occurrences of phenomena, such as necking, pore formation/filling, dislocation accumulation/decomposition, and particle rotation/rearrangement are accelerated. Based on tensile test results, Young's modulus of the as-sintered Al0.3CoCrFeNi high-entropy alloy is calculated to be 214.11 ± 1.03 GPa, which deviates only 0.82% from the experimental value, thus further validating the feasibility and accuracy of the multiparticle model. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results