Multi-Agent Collaboration via Reward Attribution Decomposition.

Tianjun Zhang Huazhe Xu Xiaolong Wang Yi Wu Kurt Keutzer Joseph E. Gonzalez Yuandong Tian

Published in: CoRR (2020)

Keyphrases

multi agent
reinforcement learning
multi agent systems
intelligent agents
decomposition method
multiagent systems
cooperative

information sharing
collaborative environment
software agents
collaborative learning
team formation
multi agent coordination
collective intelligence

multi agent architecture
cooperative agents
heterogeneous agents
cross disciplinary
multiple perspectives
oriented programming
single agent

reward function
multiple agents
neural network
markov decision processes
autonomous agents
knowledge management
decision making