.png){kind=icon}
Return
Multi-Dueling framework for multi-agent reinforcement learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2025.113464.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• MDF utilizes the decomposition formula to decompose the joint action value function. • MDF introduces the V-IGM principle to enforce constraints on the value of the state value function. • MDF encodes the consistency constraints directly into the neural network, achieving strict IGM consistency.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSaveShareSave no more
no more