|
已选(0)清除
条数/页： 排序方式： |
| SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2024, 卷号: 31, 页码: 421-425
作者: Wang, Fangyuan ; Xu, Bo; Xu, Bo
  收藏 | 浏览/下载：0/0 | 提交时间：2024/07/03
Convolution Complexity theory Computational modeling Decoding Training Kernel Transformers Conformer streaming ASR sequentially sampled chunks chunked causal convolution linear complexity |
| Towards Zero-Shot Generalization: Mutual Information-Guided Hierarchical Multi-Agent Coordination 会议论文
, 日本, 2024-6
作者: Zhang Qingyang; Xu Bo
 Adobe PDF(8862Kb) | 收藏 | 浏览/下载：8/4 | 提交时间：2024/06/25
强化学习，分层强化学习 |
| Balancing Exploration and Exploitation in Hierarchical Reinforcement Learning via Latent Landmark Graphs 会议论文
, 澳大利亚, 2023-6
作者: Zhang Qingyang; Yang Yiming; Ruan Jingqing; Xiong Xuantang; Xing Dengpeng; Xu Bo
Adobe PDF(7948Kb) | 收藏 | 浏览/下载：9/5 | 提交时间：2024/06/25
强化学习，分层强化学习 |
| SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2024, 页码: 421-425
作者: Wang FY(王方圆); Xu B(徐博); Xu B(徐波)
Adobe PDF(1843Kb) | 收藏 | 浏览/下载：32/6 | 提交时间：2024/06/12 |
| Learning in bi-level markov games 会议论文
, Padua, Italy, 2022.7.18-2022.7.23
作者: Meng Linghui; Ruan Jingqing; Xing Dengpeng; Xu Bo
Adobe PDF(1450Kb) | 收藏 | 浏览/下载：21/5 | 提交时间：2024/06/11 |
| M3: Modularization for Multi-task and Multi-agent Offline Pre-training 会议论文
, London, United Kingdom, 2023.5.29-2023.6.2
作者: Meng Linghui; Ruan Jingqing; Xiong Xuantang; Li Xiyun; Zhang Xi; Xing Dengpeng; Xu Bo
Adobe PDF(1302Kb) | 收藏 | 浏览/下载：18/4 | 提交时间：2024/06/11 |
| Filtered Observations for Model-Based Multi-agent Reinforcement Learning 会议论文
, Turin, Italy, 2023.9.18-2023.9.22
作者: Meng Linghui; Xiong Xuantang; Zang Yifan; Zhang Xi; Li Guoqi; Xing Dengpeng; Xu Bo
Adobe PDF(841Kb) | 收藏 | 浏览/下载：25/9 | 提交时间：2024/06/11 |
| A New Pre-Training Paradigm for Offline Multi-Agent Reinforcement Learning with Suboptimal Data 会议论文
, Seoul, Korea, 2024.4.14-2024.4.19
作者: Meng Linghui; Zhang Xi; Xing Dengpeng; Xu Bo
Adobe PDF(964Kb) | 收藏 | 浏览/下载：20/6 | 提交时间：2024/06/11 |
| Enhancing Multi-agent Coordination via Dual-channel Consensus 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 2, 页码: 349-368
作者: Qingyang Zhang; Kaishen Wang; Jingqing Ruan; Yiming Yang; Dengpeng Xing; Bo Xu
Adobe PDF(4997Kb) | 收藏 | 浏览/下载：49/14 | 提交时间：2024/04/23
Multi-agent reinforcement learning, contrastive representation learning, consensus, multi-agent cooperation, cognitive consistency |
| Offline Pre-trained Multi-agent Decision Transformer 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 2, 页码: 233-248
作者: Linghui Meng; Muning Wen; Chenyang Le; Xiyun Li; Dengpeng Xing; Weinan Zhang; Ying Wen; Haifeng Zhang; Jun Wang; Yaodong Yang; Bo Xu
Adobe PDF(2121Kb) | 收藏 | 浏览/下载：44/12 | 提交时间：2024/04/23
Pre-training model multi-agent reinforcement learning (MARL) decision making transformer offline reinforcement
learning |
