Multi-Task Reinforcement Learning With Attention-Based Mixture of Experts-Reference-Cited by-同舟云学术

Multi-Task Reinforcement Learning With Attention-Based Mixture of Experts

Published:2023-06 Issue:6 Volume:8 Page:3812-3819
ISSN:2377-3766
Container-title:IEEE Robotics and Automation Letters
language:
Short-container-title:IEEE Robot. Autom. Lett.

Author:

Cheng Guangran¹^ORCID,Dong Lu²^ORCID,Cai Wenzhe¹^ORCID,Sun Changyin¹^ORCID

Affiliation:

1. School of Automation, Southeast University, Nanjing, China

2. School of Cyber Science and Engineering, Southeast University, Nanjing, China

Funder

National Key R&D Program of China

National Natural Science Foundation of China

Zhishan” Scholars Programs of Southeast University

Fundamental Research Funds for the Central Universities

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Artificial Intelligence,Control and Optimization,Computer Science Applications,Computer Vision and Pattern Recognition,Mechanical Engineering,Human-Computer Interaction,Biomedical Engineering,Control and Systems Engineering

Link

http://xplorestaging.ieee.org/ielx7/7083369/10102643/10111062.pdf?arnumber=10111062

Reference32 articles.

1. Efficient Multi-Task Learning via Iterated Single-Task Transfer

2. Distral: Robust multitask reinforcement learning;teh;Proc 31st Int Conf Neural Inf Process Syst,0

3. Pseudo-task augmentation: From deep multitask learning to intratask sharing—and back;meyerson;Proc Int Conf Mach Learn,0

4. Evolutionary architecture search for deep multitask networks

5. RoBERTa: A robustly optimized bert pretraining approach;liu,2019

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Robust circuit optimization under PVT variations via weight optimization problem reformulation;Expert Systems with Applications;2024-08

2. Reinforcement Learning With Adaptive Policy Gradient Transfer Across Heterogeneous Problems;IEEE Transactions on Emerging Topics in Computational Intelligence;2024-06

3. Projected Task-Specific Layers for Multi-Task Reinforcement Learning;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

4. Active reinforcement learning versus action bias and hysteresis: control with a mixture of experts and nonexperts;PLOS Computational Biology;2024-03-29

5. A lightweight multi-task learning network based on key area guidance for counterfeit detection;Signal, Image and Video Processing;2024-03-20