Decentralization of Multiagent Policies by Learning What to Communicate.

James Paulos Steven W. Chen Daigo Shishika Vijay Kumar

Published in: CoRR (2019)

Keyphrases

reinforcement learning
learning algorithm
multi agent
learning tasks
prior knowledge
unsupervised learning
learning problems
learning scheme
neural network
information systems
training data
online learning
inductive learning
inductive inference
policy gradient methods