Hiroshi Osada Satoshi Fujita CHQ: A Multi-Agent Reinforcement Learning Scheme CHQ: A Multi-Agent Reinforcement Learning Scheme. 17-23 2004 conf/iat/2004 IAT http://csdl.computer.org/comp/proceedings/iat/2004/2101/00/21010017abs.htm db/conf/iat/iat2004.html#OsadaF04