已选(0)清除
条数/页: 排序方式: |
| NExT-OOD: Overcoming Dual Multiple-Choice VQA Biases 期刊论文 IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 页码: 1913-1931 作者: Zhang Xi(张熙); Feifei Zhang; Changsheng Xu Adobe PDF(4719Kb)  |  收藏  |  浏览/下载:19/5  |  提交时间:2024/07/08 |
| 面向多模态语义理解与推理的视觉问答研究 学位论文 , 2024 作者: 张熙 Adobe PDF(39126Kb)  |  收藏  |  浏览/下载:16/1  |  提交时间:2024/07/08 多模态 视觉问答 语义挖掘 可靠关联 推理泛化 |
| Review on Peg-in-Hole Insertion Technology Based on Reinforcement Learning 会议论文 , Chongqing, China, 2023-11 作者: Shen Liancheng; Su Jianhua; Zhang Xiaodong Adobe PDF(254Kb)  |  收藏  |  浏览/下载:23/11  |  提交时间:2024/06/24 —Robot Peg-in-hole Insertion Reinforcement Learning Meta-Reinforcement Learning |
| Discovering Latent Variables for the Tasks With Confounders in Multi-Agent Reinforcement Learning 期刊论文 IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 7, 页码: 1591-1604 作者: Kun Jiang; Wenzhang Liu; Yuanda Wang; Lu Dong; Changyin Sun Adobe PDF(2128Kb)  |  收藏  |  浏览/下载:32/11  |  提交时间:2024/06/07 Latent variable model maximum entropy multi-agent reinforcement learning (MARL) multi-agent system |
| 基于知识对齐与蒸馏的持续学习方法研究 学位论文 , 2024 作者: 李焜炽 Adobe PDF(116614Kb)  |  收藏  |  浏览/下载:57/9  |  提交时间:2024/06/05 持续学习 灾难性遗忘 知识对齐 级联的知识蒸馏框架 一对多信息匹配 |
| Boosting On-Policy Actor–Critic With Shallow Updates in Critic 期刊论文 IEEE Transactions on Neural Networks and Learning Systems, 2024, 页码: 1-10 作者: Luntong Li; Yuanheng Zhu Adobe PDF(9953Kb)  |  收藏  |  浏览/下载:29/10  |  提交时间:2024/06/05 |
| MAT: Morphological Adaptive Transformer for Universal Morphology Policy Learning 期刊论文 IEEE Transactions on Cognitive and Developmental Systems, 2024, 页码: 1-12 作者: Boyu Li; Haran Li; Yuanheng Zhu; Dongbin Zhao Adobe PDF(9953Kb)  |  收藏  |  浏览/下载:21/7  |  提交时间:2024/06/05 |
| FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game 期刊论文 IEEE Transactions on Emerging Topics in Computational Intelligence, 2024, 页码: 1-13 作者: Guangzheng Hu; Yuanheng Zhu; Haoran Li; Dongbin Zhao Adobe PDF(2144Kb)  |  收藏  |  浏览/下载:32/4  |  提交时间:2024/06/05 Games Q-learning Task analysis Optimization Convergence Training Nash equilibrium Multi-agent reinforcement learning minimax-Q learning two-team zero-sum Markov games |
| Efficient Calibration of Agent-Based Traffic Simulation Using Variational Auto-Encoder 会议论文 无, Macau, China, Oct. 08-12, 2022 作者: Peijun Ye; Fenghua Zhu; Yisheng Lv; Xiao Wang; Yuanyuan Chen Adobe PDF(1928Kb)  |  收藏  |  浏览/下载:37/13  |  提交时间:2024/06/03 Agent-Based Model Calibration |
| Self-Supervised Representation Learning from Arbitrary Scenarios 会议论文 , 美国西雅图, 2024 作者: Li, Zhaowen; Zhu, Yousong; Chen, Zhiyang; Gao, Zongxin; Zhao, Chaoyang; Zhao, Rui; Tang, Ming; Wang, Jinqiao Adobe PDF(7423Kb)  |  收藏  |  浏览/下载:57/23  |  提交时间:2024/05/30 |