Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning over Noisy Channels

no code implementations • 2 Jan 2021 • Tze-Yang Tung, Szymon Kobus, Joan Roig Pujol, Deniz Gunduz

Specifically, we consider a multi-agent partially observable Markov decision process (MA-POMDP), in which the agents, in addition to interacting with the environment can also communicate with each other over a noisy communication channel.

Multi-agent Reinforcement Learning reinforcement-learning +1