中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共7条，第1-7条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
UNMAS: Multiagent Reinforcement Learning for Unshaped Cooperative Scenarios 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 12
作者:  Chai, Jiajun;  Li, Weifan;  Zhu, Yuanheng;  Zhao, Dongbin;  Ma, Zhe;  Sun, Kewu;  Ding, Jishiyu
Adobe PDF(3402Kb)  |  收藏  |  浏览/下载：274/32  |  提交时间：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  
Meta-Prototypical Learning for Domain-Agnostic Few-Shot Recognition 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 1-7
作者:  Wang RQ(王瑞琪);  Zhang XY(张煦尧);  Liu CL(刘成林)
Adobe PDF(1403Kb)  |  收藏  |  浏览/下载：263/52  |  提交时间：2022/01/27
domain-agnostic few-shot recognition  image classification  meta-learning  prototypical 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
作者:  Hu, Guangzheng;  Zhu, Yuanheng;  Zhao, Dongbin;  Zhao, Mengchen;  Hao, Jianye
Adobe PDF(4187Kb)  |  收藏  |  浏览/下载：241/7  |  提交时间：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)  
Spiking Adaptive Dynamic Programming Based on Poisson Process for Discrete-Time Nonlinear Systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 11
作者:  Wei, Qinglai;  Han, Liyuan;  Zhang, Tielin
Adobe PDF(2904Kb)  |  收藏  |  浏览/下载：220/9  |  提交时间：2022/01/27
Maximum likelihood estimation (MLE)  Nonlinear systems  Optimal control  Poisson process  Spike train  Spiking Adaptive dynamic programming（SADP）  
Neuro-Optimal Trajectory Tracking With Value Iteration of Discrete-Time Nonlinear Dynamics 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 12
作者:  Wang, Ding;  Ha, Mingming;  Cheng, Long
收藏  |  浏览/下载：273/0  |  提交时间：2022/01/27
Trajectory  Heuristic algorithms  Convergence  Trajectory tracking  Stability criteria  Optimal control  Dynamic programming  Adaptive critic design  discrete-time nonlinear plants  neuro-optimal trajectory tracking  uniformly ultimately bounded stability  value iteration  
Decentralized Event-Driven Constrained Control Using Adaptive Critic Designs 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 15
作者:  Yang, Xiong;  Zhu, Yuanheng;  Dong, Na;  Wei, Qinglai
Adobe PDF(1578Kb)  |  收藏  |  浏览/下载：224/10  |  提交时间：2022/01/27
Adaptive critic designs (ACDs)  adaptive dynamic programming (ADP)  decentralized event-driven control  input constraint  reinforcement learning (RL)  
EDP: An Efficient Decomposition and Pruning Scheme for Convolutional Neural Network Compression 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 10, 页码: 4499-4513
作者:  Ruan, Xiaofeng;  Liu, Yufan;  Yuan, Chunfeng;  Li, Bing;  Hu, Weiming;  Li, Yangxi;  Maybank, Stephen
Adobe PDF(3625Kb)  |  收藏  |  浏览/下载：340/45  |  提交时间：2021/06/17
Data-driven  low-rank decomposition  model compression and acceleration  structured pruning