CASIA OpenIR

Browse/Search Results:  1-10 of 20 Help

Selected(0)Clear Items/Page:    Sort:
平行学习理论及其在智能交通系统中的应用 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  林懿伦
Adobe PDF(17378Kb)  |  Favorite  |  View/Download:172/1  |  Submit date:2019/07/15
平行学习  强化学习  深度学习  智能交通系统  
基于深度强化学习的游戏智能决策 学位论文
工学博士学位, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  邵坤
Adobe PDF(13984Kb)  |  Favorite  |  View/Download:233/7  |  Submit date:2019/06/27
深度强化学习  深度学习  强化学习  智能决策  游戏人工智能  多智能体系统  
StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning 期刊论文
IEEE Transactions on Emerging Topics in Computational Intelligence, 2019, 卷号: 3, 期号: 1, 页码: 73-84
Authors:  Kun Shao;  Yuanheng Zhu;  Dongbin Zhao
View  |  Adobe PDF(4125Kb)  |  Favorite  |  View/Download:83/46  |  Submit date:2019/04/22
Reinforcement Learning, Transfer Learning, Curriculum Learning, Neural Network, Game Ai  
Finite Sample Analysis of LSTD with Random Projections and Eligibility Traces 会议论文
, Stockholm, Sweden, July 13-19 2018
Authors:  Li HF(李海芳);  Yingce Xia;  Wensheng Zhang
View  |  Adobe PDF(173Kb)  |  Favorite  |  View/Download:17/3  |  Submit date:2019/10/07
Visual navigation with Actor-Critic deep reinforcement learning 会议论文
, Rio, Brazil, 2018-01
Authors:  Kun Shao;  Dongbin Zhao;  Yuanheng Zhu;  Qichao Zhang
View  |  Adobe PDF(1827Kb)  |  Favorite  |  View/Download:73/42  |  Submit date:2019/04/22
面向几类微分博弈的自适应动态规划方法 学位论文
, 北京: 中国科学院研究生院, 2017
Authors:  Zhang,Qichao
Adobe PDF(4868Kb)  |  Favorite  |  View/Download:146/11  |  Submit date:2017/06/07
自适应动态规划  神经网络  微分博弈  
Improving learning efficiency of recurrent neural network through adjusting weights of all layers in a biologically-inspired framework 会议论文
, Anchorage, Alaska, 14-19 May 2017
Authors:  Xiao Huang;  Wei Wu;  Peijie Yin;  Hong Qiao
View  |  Adobe PDF(463Kb)  |  Favorite  |  View/Download:100/23  |  Submit date:2018/01/06
Cooperative Reinforcement Learning for Multiple Units Combat in StarCraft 会议论文
, Honolulu, Hawaii, USA, Nov. 27 to Dec 1, 2017
Authors:  Shao K(邵坤);  Zhu YH(朱圆恒);  Zhao DB(赵冬斌)
View  |  Adobe PDF(1378Kb)  |  Favorite  |  View/Download:211/120  |  Submit date:2017/09/20
Model-Free Optimal Tracking Control via Critic-Only Q-Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 卷号: 27, 期号: 10, 页码: 2134-2144
Authors:  Luo, Biao;  Liu, Derong;  Huang, Tingwen;  Wang, Ding;  Luo,Biao
View  |  Adobe PDF(1521Kb)  |  Favorite  |  View/Download:216/111  |  Submit date:2016/10/24
Critic-only Q-learning (Coql)  Model-free  Nonaffine Nonlinear Systems  Optimal Tracking Control  
基于监督式自适应动态规划的车辆智能巡航控制 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2015
Authors:  王滨
Adobe PDF(2069Kb)  |  Favorite  |  View/Download:555/2  |  Submit date:2015/09/02
自适应巡航控制  自适应动态规划  监督式强化学习  智能控制  Dspace  Adaptive Cruise Control  Adaptive Dynamic Programming  Supervised Reinforcement Learning  Intelligent Control  Dspace