A multi-agent reinforcement learning method for a partially-observable competitive game.

Yoichiro Matsuno Tatsuya Yamazaki Shin Ishii A multi-agent reinforcement learning method for a partially-observable competitive game. 39-40 2001 Agents http://portal.acm.org/citation.cfm?id=375735.375856 db/conf/agents/agents2001.html#MatsunoYIM01