CASIA OpenIR

Browse/Search Results:  1-10 of 215 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Highway Lane Change Decision-Making via Attention-Based Deep Reinforcement Learning 期刊论文
IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2022, 卷号: 9, 期号: 3, 页码: 567-569
Authors:  Wang, Junjie;  Zhang, Qichao;  Zhao, Dongbin
Adobe PDF(803Kb)  |  Favorite  |  View/Download:29/2  |  Submit date:2022/02/16
Online Minimax Q Network Learning for Two-Player Zero-Sum Markov Games 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 33, 期号: 3, 页码: 1228-1241
Authors:  Zhu, Yuanheng;  Zhao, Dongbin
Favorite  |  View/Download:27/0  |  Submit date:2022/06/10
Games  Nash equilibrium  Mathematical model  Markov processes  Convergence  Dynamic programming  Training  Deep reinforcement learning (DRL)  generalized policy iteration (GPI)  Markov game (MG)  Nash equilibrium  Q network  zero sum  
Boost 3-D Object Detection via Point Clouds Segmentation and Fused 3-D GIoU-L-1 Loss 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 33, 期号: 2, 页码: 762-773
Authors:  Chen, Yaran;  Li, Haoran;  Gao, Ruiyuan;  Zhao, Dongbin
Favorite  |  View/Download:18/0  |  Submit date:2022/03/17
3-D object detection  generalized Intersection of Union (GIoU) loss  segmentation  
BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search 期刊论文
IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS, 2022, 卷号: 0, 期号: 0, 页码: 0
Authors:  Zixiang, Ding;  Yaran, Chen;  Nannan, Li;  Dongbin, Zhao
Adobe PDF(7657Kb)  |  Favorite  |  View/Download:29/1  |  Submit date:2022/01/07
Broad neural architecture search (BNAS), continuous relaxation, confident learning rate, partial channel connections, image classification.  
Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 卷号: 0, 期号: 0, 页码: 0
Authors:  Zixiang, Ding;  Yaran, Chen;  Nannan, Li;  Dongbin, Zhao;  C.L.Philip Chen,
Adobe PDF(764Kb)  |  Favorite  |  View/Download:29/5  |  Submit date:2022/01/07
broad neural architecture search, stacked broad convolutional neural network, knowledge embedding search, image classification.  
Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target 期刊论文
COMPLEX & INTELLIGENT SYSTEMS, 2021, 页码: 12
Authors:  Li, Weifan;  Zhu, Yuanheng;  Zhao, Dongbin
Favorite  |  View/Download:22/0  |  Submit date:2021/12/28
Reinforcement learning  Missile guidance  Auxiliary learning  Self-imitation learning  
Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 13
Authors:  Hu, Guangzheng;  Zhu, Yuanheng;  Zhao, Dongbin;  Zhao, Mengchen;  Hao, Jianye
Favorite  |  View/Download:16/0  |  Submit date:2022/01/27
Bandwidth  Protocols  Reinforcement learning  Task analysis  Optimization  Communication networks  Multi-agent systems  Event trigger  limited bandwidth  multi-agent communication  multi-agent reinforcement learning (MARL)  
BiFNet: Bidirectional Fusion Network for Road Segmentation 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2021, 页码: 12
Authors:  Li, Haoran;  Chen, Yaran;  Zhang, Qichao;  Zhao, Dongbin
Favorite  |  View/Download:19/0  |  Submit date:2022/01/27
Roads  Image segmentation  Three-dimensional displays  Cameras  Laser radar  Fuses  Feature extraction  Adaptive learning  autonomous vehicles  multisensor fusion  road segmentation  
UNMAS: Multiagent Reinforcement Learning for Unshaped Cooperative Scenarios 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 12
Authors:  Chai, Jiajun;  Li, Weifan;  Zhu, Yuanheng;  Zhao, Dongbin;  Ma, Zhe;  Sun, Kewu;  Ding, Jishiyu
Favorite  |  View/Download:21/0  |  Submit date:2022/01/27
Multi-agent systems  Training  Task analysis  Reinforcement learning  Sun  Learning systems  Semantics  Centralized training with decentralized execution (CTDE)  multiagent  reinforcement learning  StarCraft II  
Optimal Feedback Control of Pedestrian Flow in Heterogeneous Corridors 期刊论文
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2021, 卷号: 18, 期号: 3, 页码: 1097-1108
Authors:  Zhu, Yuanheng;  Zhao, Dongbin;  He, Haibo
Favorite  |  View/Download:45/0  |  Submit date:2021/08/15
Microscopy  Feedback control  Mathematical model  Data models  Dynamic programming  Psychology  Computational modeling  Adaptive dynamic programming (ADP)  heterogeneous corridors  macroscopic pedestrian dynamics  optimal feedback control  pedestrian flow