中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共2条，第1-2条 帮助

限定条件                    
已选(0)清除 条数/页：   排序方式：
An Empirical Study on Google Research Football Multi-agent Scenarios 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 3, 页码: 549-570
作者:  Yan Song;  He Jiang;  Zheng Tian;  Haifeng Zhang;  Yingping Zhang;  Jiangcheng Zhu;  Zonghong Dai;  Weinan Zhang;  Jun Wang
Adobe PDF(24588Kb)  |  收藏  |  浏览/下载：17/5  |  提交时间：2024/05/23
Multi-agent reinforcement learning (RL), distributed RL system, population-based training, reward shaping, game theory  
Sharing Weights in Shallow Layers via Rotation Group Equivariant Convolutions 期刊论文
Machine Intelligence Research, 2022, 卷号: 19, 期号: 2, 页码: 115-126
作者:  Zhiqiang Chen;  Ting-Bing Xu;  Jinpeng Li;  Huiguang He
Adobe PDF(1272Kb)  |  收藏  |  浏览/下载：24/7  |  提交时间：2024/04/23
Convolutional neural networks (CNNs)  group equivariance  higher-degree weight sharing  parameter efficiency