Paolo Puliti Guido Tascini Anna Montesanto Reactive Navigation Using Reinforment Learning in Situations of POMDPs. 444-450 2001 conf/iwann/2001-2 IWANN (2) http://link.springer.de/link/service/series/0558/bibs/2085/20850444.htm db/conf/iwann/iwann2001-2.html#PulitiTM01