CASIA OpenIR

Browse/Search Results:  1-10 of 159 Help

Selected(0)Clear Items/Page:    Sort:
Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2019, 卷号: 49, 期号: 8, 页码: 2874-2885
Authors:  Zhang, Qichao;  Zhao, Dongbin
View  |  Adobe PDF(1021Kb)  |  Favorite  |  View/Download:36/10  |  Submit date:2019/07/12
Integral reinforcement learning (IRL)  neural network (NN)  nonzero-sum (NZS) games  off-policy  single-critic  unknown drift dynamics  
类脑自主学习与决策神经网络模型 学位论文
, 中国科学院大学: 中国科学院自动化化研究所, 2019
Authors:  赵菲菲
Adobe PDF(16032Kb)  |  Favorite  |  View/Download:106/6  |  Submit date:2019/06/05
类脑自主学习与决策  多脑区协同  脉冲神经网络  发育神经网络  微观可塑性  视觉恐惧反应模型  无人机自主决策  
面向用户行为序列的深度上下文建模 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  崔强
Adobe PDF(12117Kb)  |  Favorite  |  View/Download:64/4  |  Submit date:2019/06/18
上下文信息  深度学习  用户行为序列  循环神经网络  注意力机制  
面向社交媒体的事件检测与流行度预测方法研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  陈观淡
Adobe PDF(3562Kb)  |  Favorite  |  View/Download:71/6  |  Submit date:2019/06/09
社交媒体分析  事件检测  流行度预测  事件相关关系  表示学习  
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:182/7  |  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  
Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving 期刊论文
IEEE Computational Intelligence Magazine, IEEE Computational Intelligence Magazine, 2019, 2019, 卷号: 14, 14, 期号: 2, 页码: 83-98, 83-98
Authors:  Dong Li;  Dongbin Zhao;  Qichao Zhang;  Yaran Chen
View  |  Adobe PDF(2205Kb)  |  Favorite  |  View/Download:52/16  |  Submit date:2019/04/25
Deep Learning  Autonomous Driving  Visual Control  Reinforcement Learning  Deep Learning  Autonomous Driving  Visual Control  Reinforcement Learning  
基于自适应动态规划的可重构机器人系统分散控制方法研究 研究报告
2019
Authors:  董博
Adobe PDF(2806Kb)  |  Favorite  |  View/Download:70/1  |  Submit date:2019/03/12
可重构机器人  分散控制  自适应动态规划  滑模控制  最优控制  动力学耦合效应  关节力矩估计  谐波传动  
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:75/45  |  Submit date:2019/04/22
Reinforcement Learning, Transfer Learning, Curriculum Learning, Neural Network, Game Ai  
Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game 会议论文
, Macao, China, August 10-16, 2019
Authors:  Peixi Peng;  Junliang Xing;  Lili Cao;  Lisen Mu;  Chang Huang
View  |  Adobe PDF(762Kb)  |  Favorite  |  View/Download:31/11  |  Submit date:2019/10/10
Multi-agent Learning  Deep Decentralized Policy Network  Real-time Combat Game  
Adaptive Q-Learning for Data-Based Optimal Output Regulation With Experience Replay 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2018, 卷号: 48, 期号: 12, 页码: 3337-3348
Authors:  Luo, Biao;  Yang, Yin;  Liu, Derong
Favorite  |  View/Download:36/0  |  Submit date:2019/01/08
Data-based  experience replay  neural networks (NNs)  off-policy  optimal control  Q-learning (QL)