Reducing Q-Value Estimation Bias via Mutual Estimation and Softmax Operation in MADRL
With the development of electronic game technology, the content of electronic games presents a larger number of units, richer unit attributes, more complex game mechanisms, and more diverse team strategies. Multi-agent deep reinforcement learning shines brightly in this type of team electronic game,...
Main Authors: | Zheng Li, Xinkai Chen, Jiaqing Fu, Ning Xie, Tingting Zhao |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/17/1/36 |
Similar Items
-
Hardware Implementation of a Softmax-Like Function for Deep Learning
by: Ioannis Kouretas, et al.
Published: (2020-08-01) -
Techniques and Paradigms in Modern Game AI Systems
by: Yunlong Lu, et al.
Published: (2022-08-01) -
Hybrid-Margin Softmax for the Detection of Trademark Image Similarity
by: Chenyang Wang, et al.
Published: (2024-03-01) -
A Low-Voltage, Low-Power Reconfigurable Current-Mode Softmax Circuit for Analog Neural Networks
by: Massimo Vatalaro, et al.
Published: (2021-04-01) -
Angular Margin-Mining Softmax Loss for Face Recognition
by: Jwajin Lee, et al.
Published: (2022-01-01)