Login / Signup
POAQL: A Partially Observable Altruistic Q-Learning Method for Cooperative Multi-Agent Reinforcement Learning.
Lesong Tao
Miao Kang
Jinpeng Dong
Songyi Zhang
Ke Ye
Shitao Chen
Nanning Zheng
Published in:
ICRA (2024)
Keyphrases
</>
cooperative
multi agent reinforcement learning
reinforcement learning
objective function
dynamic programming
state space
multi agent
partially observable
probabilistic model
mathematical model
learning algorithm
knowledge base
function approximation