CASIA OpenIR

浏览/检索结果: 共50条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
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:10/5  |  提交时间:2024/06/25
强化学习,分层强化学习  
Latent Landmark Graph for Efficient Exploration-Exploitation Balance in Hierarchical Reinforcement Learning 期刊论文
Machine Intelligence Research, 2023, 页码: 158
作者:  Zhang Qingyang;  Zhang Hongming;  Xing Dengpeng;  Bo Xu
Adobe PDF(9639Kb)  |  收藏  |  浏览/下载:8/5  |  提交时间:2024/06/25
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:20/5  |  提交时间:2024/06/11
Continuous Exploration via Multiple Perspectives in Sparse Reward Environment 会议论文
, 厦门国际会议中心, 2023-10-13
作者:  Chen ZP(陈忠鹏);  Guan Q(关强)
Adobe PDF(2260Kb)  |  收藏  |  浏览/下载:27/7  |  提交时间:2024/06/04
Reinforcement Learning · Exploration Strategy · Sparse Reward · Intrinsic Motivation  
Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language. 会议论文
, 北京华腾美居酒店, 2023-12-9
作者:  Zhourui Guo;  Meng Yao;  Yang Yu;  Qiyue Yin
Adobe PDF(2302Kb)  |  收藏  |  浏览/下载:16/6  |  提交时间:2024/06/03
Class Incremental Robotic Pick-and-Place via Incremental Few-Shot Object Detection 期刊论文
IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 卷号: 8, 期号: 9, 页码: 5974-5981
作者:  Deng JR(邓杰仁);  Zhang HJ(张好剑);  Hu JH(胡建华);  Zhang XX(张兴轩);  Wang YK(王云宽)
Adobe PDF(1914Kb)  |  收藏  |  浏览/下载:60/10  |  提交时间:2024/05/31
Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control 会议论文
Advances in Neural Information Processing Systems, New Orleans, USA, 2023-12-10
作者:  Chao Li;  Chen Gong;  Qiang He;  Xinwen Hou
Adobe PDF(1457Kb)  |  收藏  |  浏览/下载:30/8  |  提交时间:2024/05/30
Reward Estimation with Scheduled Knowledge Distillation for Dialogue Policy Learning 期刊论文
Connection Science, 2023, 卷号: 35, 期号: 1, 页码: 2174078
作者:  Qiu JY(邱俊彦);  Haidong Zhang;  Yiping Yang
Adobe PDF(831Kb)  |  收藏  |  浏览/下载:35/12  |  提交时间:2024/05/29
reinforcement learning  dialogue policy learning  curriculum learning  knowledge distillation  
Learning Individual Difference Rewards in Multi-Agent Reinforcement Learning 会议论文
, London, United Kingdom, 2023-5
作者:  Yang, Chen;  Yang, Guangkai;  Zhang, Junge
Adobe PDF(2419Kb)  |  收藏  |  浏览/下载:34/12  |  提交时间:2024/05/29
Explicitly Learning Policy Under Partial Observability in Multiagent Reinforcement Learning 会议论文
, Queensland, Australia, 2023-6
作者:  Yang, Chen;  Yang, Guangkai;  Chen, Hao;  Zhang, Junge
Adobe PDF(3027Kb)  |  收藏  |  浏览/下载:42/17  |  提交时间:2024/05/29