Daisuke Kitakoshi Hiroyuki Shioya Masahito Kurihara Analysis of a Method Improving Reinforcement Learning Agents' Policies. 276-282 2003 7 JACIII 3 http://www.fujipress.jp/finder/xslt.php?mode=present&inputfile=JACII000700030004.xml db/journals/jaciii/jaciii7.html#KitakoshiSK03