02/02/2021

Inference-Based Deterministic Messaging For Multi-Agent Communication

Varun Bhatt, Michael Buro

Keywords:

Abstract Paper Similar Papers

Abstract: Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study learning in matrix-based signaling games to empirically show that decentralized methods can converge to a suboptimal policy. We then propose a modification to the messaging policy, in which the sender deterministically chooses the best message that helps the receiver to infer the sender's observation. Using this modification, we see, empirically, that the agents converge to the optimal policy in nearly all the runs. We then apply this method to a partially observable gridworld environment which requires cooperation between two agents and show that, with appropriate approximation methods, the proposed sender modification can enhance existing decentralized training methods for more complex domains as well.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949280
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:25 
 0
 0
 0
 0
 12:55 
 0
 0
 0
 0
 12:41 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 9:23 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:40 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 6:54 
 0
 0
 0
 0
 12:28 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:53 
 0
 0
 0
 0
 8:10 
 0
 0
 0
 0
 5:23 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 13:42 
 0
 0
 0
 0
 19:59 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 8:22 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 18:46 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 8:01 
 0
 0
 0
 0
 12:04 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 8:03 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01