TY  - RPRT
TI  - A new Q-learning algorithm based on the metropolis criterion.
AU  - Maozu Guo
AU  - Yang Liu
AU  - Jacek Malec
PY  - 2004
DO  - 10.1109/tsmcb.2004.832154
UR  - https://pubmed.ncbi.nlm.nih.gov/15503510/
ID  - 15503510
ER  -