Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning

arXiv: Artificial Intelligence, Volume abs/1710.00336, 2017.

Cited by: 12|Bibtex|Views9|Links
EI

Abstract:

Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it c...More

Code:

Data:

Your rating :
0

 

Tags
Comments