Gongju Wang

Dr. Gongju Wang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 October 2020
Verified
Conference Paper
Closed access
HJHao Jiang
Hao Jiang
DSDianxi Shi
Dianxi Shi
CXChao Xue
Chao Xue
Yajie WangYajie Wang
Yajie Wang
GWGongju Wang
Gongju Wang
ZYZhang yongjun Zhang yongjun
Zhang yongjun Zhang yongjun
In large-scale multi-agent systems, the existence of a large number of agents with different target tasks and connected by complex game relationships causes great difficulty for policy learning. Therefore, simplifying the learning process is an important issue. In multi-agent systems, agents with the same target tasks or attributes often interact more with each other and exhibit behaviors more similar. That means there are stronger collaborations between these agents. Most existing multi-agent reinforcement learning (MARL) algorithms expect to learn the collaborative strategies of all agents directly in order to maximize the common rewards. This causes the difficulty of policy learning to increase exponentially as the number and types of agents increase. To address this problem, we propose a goal-based hierarchical group communication (GHGC) algorithm. This algorithm divides the agents into different groups, and maintains the group’s cognitive consistency through knowledge sharing. Subsequently, we introduce a group communication and value decomposition method to ensure cooperation between the various groups. Experiments demonstrate that our model outperforms state-of-the-art MARL methods on the widely adopted StarCraft II benchmarks across different scenarios, and also possesses potential value for large-scale real-world applications.

19 April 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
HJHao Jiang
Hao Jiang
GWGongju Wang
Gongju Wang
SLShengze Li
Shengze Li
JZJieyuan Zhang
Jieyuan Zhang
LYLong Yan
Long Yan
XXXinhai Xu
Xinhai Xu
The large action space is a key challenge in reinforcement learning. Although hierarchical methods have been proven to be effective in addressing this issue, they are not fully explored. This paper combines domain knowledge with hierarchical concepts to propose a novel Hierarchical Reinforcement Learning framework based on macro actions (HRL-MA). This framework includes a macro action mapping model that abstracts sequences of micro actions into macro actions, thereby simplifying the decision-making process. Macro actions are divided into two categories: combat macro actions (CMA) and non-combat macro actions (NO-CMA). NO-CMA are driven by decision tree-based logical rules and provide conditions for the execution of CMA. CMA form the action space of the reinforcement learning algorithm, which dynamically selects actions based on the current state. Comprehensive tests on the StarCraft II maps Simple64 and AbyssalReefLE demonstrate that the HRL-MA framework exhibits superior performance, achieving higher win rates compared to baseline algorithms. Furthermore, in mini-game scenarios, HRL-MA consistently outperforms baseline algorithms in terms of reward scores. The findings highlight the effectiveness of integrating hierarchical structures and macro actions in reinforcement learning to manage complex decision-making tasks in environments with large action spaces.

21 November 2024
Verified
Conference Paper
Open access
YSYulun Song
Yulun Song
LYLong Yan
Long Yan
LQLina Qin
Lina Qin
GWGongju Wang
Gongju Wang
XHXingru Huang
Xingru Huang
WLWeixin Liu
Weixin Liu

10 August 2025
Verified
Book Chapter
Closed access
PDF file
MNMingjian Ni
Mingjian Ni
GWGongju Wang
Gongju Wang
YSYinghao Song
Yinghao Song
YLYang Li
Yang Li
LYLong Yan
Long Yan
YSyulun song
yulun song

5 November 2023
Verified
Book Chapter
Closed access
PDF file
MLMengyao Li
Mengyao Li
YSYinghao Song
Yinghao Song
LYLong Yan
Long Yan
HFHanbin Feng
Hanbin Feng
YSYulun Song
Yulun Song
GWGongju Wang
Gongju Wang