TY  - RPRT
TI  - A statistical property of multiagent learning based on Markov decision process.
AU  - Kazunori Iwata
AU  - Kazushi Ikeda
AU  - Hideaki Sakai
PY  - 2006
DO  - 10.1109/tnn.2006.875990
UR  - https://pubmed.ncbi.nlm.nih.gov/16856649/
ID  - 16856649
ER  -