.png){kind=icon}
返回
Lateral Transfer Learning for Multiagent Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2021.3108237.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Some researchers have introduced transfer learning mechanisms to multiagent reinforcement learning (MARL). However, the existing works devoted to cross-task transfer for multiagent systems were designed just for homogeneous agents or similar domains. This work proposes an all-purpose cross-transfer method, called multiagent lateral transfer (MALT), assisting MARL with alleviating the training burden. We discuss several challenges in developing an all-purpose multiagent cross-task transfer learning method and provide a feasible way of reusing knowledge for MARL. In the developed method, we take features as the transfer object rather than policies or experiences, inspired by the progressive network. To achieve more efficient transfer, we assign pretrained policy networks for agents based on clustering, while an attention module is introduced to enhance the transfer framework. The proposed method has no strict requirements for the source task and target task. Compared with the existing works, our method can transfer knowledge among heterogeneous agents and also avoid negative transfer in the case of fully different tasks. As far as we know, this article is the first work denoted to all-purpose cross-task transfer for MARL. Several experiments in various scenarios have been conducted to compare the performance of the proposed method with baselines. The results demonstrate that the method is sufficiently flexible for most settings, including cooperative, competitive, homogeneous, and heterogeneous configurations.
Keyword:
Task analysis
Transfer learning
Training
Reinforcement learning
Neural networks
Multi-agent systems
Costs
Attention mechanism
multiagent reinforcement learning (MARL)
transfer learning
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
A Cross-Modal Investigation of Spatial Performances in Patients with Unilateral Cerebral Disease.png)
Cortex
OAAI
CortexIF0
OAAI分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Finite-Time Adaptive Fuzzy Control for MIMO Nonlinear Systems With Input Saturation via Improved Command-Filtered Backstepping输入饱和MIMO非线性系统的改进指令滤波反步法有限时间自适应模糊控制
PREAI
分享收藏
查看更多内容