Learning Generalizable Risk-Sensitive Policies to Coordinate in Decentralized Multi-Agent General-Sum Games.

Ziyi Liu Xian Guo Yongchun Fang

Published in: CoRR (2022)

Keyphrases

multi agent
learning agents
risk sensitive
cooperative
learning tasks
neural network
reinforcement learning
optimal control
learning algorithm
multi agent systems
learning process
dynamic programming
state space
sufficient conditions
multiagent systems
finite state